inputs
stringlengths 38
563k
| targets
stringlengths 0
13.8k
| task_source
stringclasses 1
value | task_name
stringlengths 19
85
| template_type
stringclasses 2
values |
|---|---|---|---|---|
You will be given a statement and two events in Croatian. The events are either something that can be caused by the statement, or they are something that might have caused the statement. If they can be consequences of the statement, answer with "effect", else answer with "cause".
[EX Q]: Statement: Žena se udarila o dvosjed.
Choice 1: Noga dvosjeda se olabavila.
Choice 2: Natukla je koljeno.
[EX A]: effect
[EX Q]: Statement: Ključ mi je nestao iz džepa hlača.
Choice 1: Džep je imao rupu.
Choice 2: Hlače su bile nove.
[EX A]: cause
[EX Q]: Statement: Pećnica se zagrijala.
Choice 1: Upalio sam pećnicu.
Choice 2: Stavio sam jelo u pećnicu.
[EX A]: | cause
| NIv2 | task1627_copa_hr_classification | fs_opt |
In this task, you need to count the number of nouns/verbs in the given sentence.
--------
Question: Sentence: 'A red train engine coming into a station'. Count the number of nouns in this sentence.
Answer: 3
Question: Sentence: 'a bathroom view of a tiolet, bathtub sitting on a tiled floor'. Count the number of nouns in this sentence.
Answer: 5
Question: Sentence: 'A closeup of a pizza with whole tomato slices'. Count the number of nouns in this sentence.
Answer: | 4
| NIv2 | task155_count_nouns_verbs | fs_opt |
Detailed Instructions: In this task, you are given a short passage that conveys stereotype or anti-stereotype about a specific target. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into four types of stereotype or anti-stereotype: gender, profession, race, and religion.
Problem:Passage: Did you know that a mathematician lives on Sally's street? She wears the cutest dresses and likes to go out dancing.
Solution: | Profession | NIv2 | task280_stereoset_classification_stereotype_type | zs_opt |
TASK DEFINITION: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.
PROBLEM: What is the continues to place of the line that is displayed in the color purple on station placards , the formal subway map , and internal route maps in R188 cars ?
SOLUTION: Queens
PROBLEM: When was the city where the oldest championship record was set founded ?
SOLUTION: 1812
PROBLEM: What company took over the station with the lowest UHF number ?
SOLUTION: | Viacom
| NIv2 | task344_hybridqa_answer_generation | fs_opt |
instruction:
Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer "Yes", otherwise "No".
question:
Question1: Why do people ask so many Googleable questions on Quora?, Question2: Why do people ask stupid questions on Quora that could be easily answered by Google?
answer:
Yes
question:
Question1: What's a good Joke?, Question2: What are the best jokes in the US?
answer:
No
question:
Question1: What calms mind?, Question2: What is the best way to keep your mind calm?
answer:
| No
| NIv2 | task1287_glue_qqp_paraphrasing | fs_opt |
In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions of the participants in the sentence and those affected by it. Is any of these emotions caused by the sentence? You should write your answer in the form " A >Causes> B". Try to use phrases and sentences from the story to compose your answer when possible. For the sentence describing the result, you must use the verb feel(s).
One example: story: Our neighbors down the hall had a very noisy party. One of the guests passed out in front of my door. When I asked him to leave he swore at me. I called the police. The guest left before the police came.
selected sentence: When I asked him to leave he swore at me.
Solution is here: I ask him to leave >Causes> He feel(s) angered
Explanation: The emotion caused by the sentence can be anger or being upset, as the person involved swears. This is a good answer.
Now, solve this: story: David had a bad toothache. He made an appointment with the dentist. The next week the dentist had to pull his tooth. David went home very sore to recover. The next day David felt much better without the pain.
selected sentence: The next week the dentist had to pull his tooth.
Solution: | The dentist has to pull his tooth >Causes> David feel(s) pained | NIv2 | task749_glucose_reverse_cause_emotion_detection | fs_opt |
Detailed Instructions: In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e. tagset of this corpus is 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, 'PART': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.
Q: Sentence: The Gu'ud family {{ even }} accepted to be offered the seat of Al - Anbar governor some months back .
Word: even
A: | ADV | NIv2 | task583_udeps_eng_coarse_pos_tagging | zs_opt |
Part 1. Definition
In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
Part 2. Example
#RPDR FUCKING FARRAH MOAN, HAVE YOU NEVER WATCHED THIS SHOW. WHEN YOU GET THE CALL, TAKE A LESSON.
Answer: Yes
Explanation: (Correct Answer) This post is aggressive and berates a person for not having watched a show. Therefore the correct answer is 1/Potentially Offensive.
Part 3. Exercise
RT @HeidiL_RN: Fuck Islam you pigfucking trash troll. @ItsJustMe7o7 @MzKeriEvans @ctbauza
Answer: | Yes | NIv2 | task609_sbic_potentially_offense_binary_classification | fs_opt |
In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding "Yes". Otherwise, respond "No". There are only two types of responses possible:"Yes" and "No".
Paragraph- Sent 1: Sam Farragut is a sociopathic business executive in Southern California who forces a team of advertising agency employees to embark on a dangerous dirtbike trip to the Baja California desert in order to compete for his business .
Sent 2: The men are Warren Summerfield , a suicidal middle-aged ad executive who has been fired from the agency ; the straightlaced Paul McIlvain who is inattentive to his wife , and brash art designer Maxon who feels suddenly trapped after his girlfriend announces she is pregnant .
Sent 3: There are numerous long sequences of motorcycle riding on desert backroads .
Sent 4: Summerfield has been having an affair with McIlvian 's wife .
Sent 5: He has not told his wife that he was fired and is simply serving out his tenure at the agency while looking for a new position .
Sent 6: His wife is actually aware of the affair .
Sent 7: Farragut convinces the ad men to make the motorcycle journey on the pretext of looking for a location to shoot a commercial .
Sent 8: In reality , Farragut is reckless and looking to involve the men in spontaneous edgy adventure of his own manipulation .
Sent 9: After they leave , McIlvain 's wife suspects that Summerfield is planning to kill himself for the insurance money , but she can not convince Summerfield 's wife to instigate a search .
Sent 10: The four men travel deeper into Mexico on isolated dirt roads .
Sent 11: At one point Summerfield contemplates plunging off a cliff .
Sent 12: After being humiliated by a young American couple in a Baja bar , Farragut tracks them down on the beach while accompanied by Maxon .
Question: Who is Summerfield having an affair with and does his wife know that he is having an affair?
Incorrect Answer: Maxon.
Yes.
Paragraph- Sent 1: The opening shot of the movie shows Kunti praying for Lord Krishna 's protection for the Pandavas .
Sent 2: Lord Krishna consoles Kunti and promises to ever protect the Pandavas and guide them through troubles and problems that may occur in life .
Sent 3: The sons of Pandu and Dhritarashtra progeny break into an argument .
Sent 4: When Duryodhana insults the Pandavas as `` dependents '' , Bheema counters by saying that , the Kauravas are the progeny of a widow .
Sent 5: Duryodhana asks Veda Vyasa for an explanation .
Sent 6: He is then told that , since his mother , Gandhari had an astrological defect , she is first married of to a goat and then married to his father .
Sent 7: Duryodhana gains animosity towards the kingdom of Gandhara where the king , the father of his mother Gandhari , rules .
Sent 8: He attacks Gandhara and lays waste of the whole kingdom .
Sent 9: He them imprisons the royal family in his prison .
Sent 10: He gives them only one rice grain per prisoner .
Sent 11: The king of Gandhara then stops everyone from grabbing the little food that is provided .
Sent 12: He says that instead of everyone dying , they could keep at least one of their princes alive .
Sent 13: He chooses Sakuni to be alive .
Sent 14: Sakuni takes an oath that he will do everything he can to destroy the entire Kaurava clan .
Sent 15: He makes magic dice from his father 's spinal cord .
Sent 16: The magic dice show exactly the number that he would want .
Sent 17: Duryodhana takes pity on the lone prisoner , Sakuni after the rest of the Gandhara royal family dies in prison out of starvation .
Sent 18: Sakuni joins the evil of coterie of Duryodhana , Karna and Dushyasana .
Question: Who attacked the kingdom of Gandhara?
Incorrect Answer: c.
Yes.
Paragraph- Sent 1: Fatty plays a somewhat lazy young man who disrupts his mother 's life by causing a fire by smoking in bed , then ruins laundry day by dropping it in the mud .
Sent 2: He has two loves of his life , the girl next door Lizzie and his dog Luke .
Sent 3: After showcasing his lack of talents helping his mother , he is able to save Luke from the dog catchers and express his love for Lizzie through a hole in the fence .
Sent 4: In the second reel , Fatty , Lizzie , mom and Luke go to the amusement park , where Fatty is first outwitted by a couple of sharks but then retrieves his losses by pointing a fake gun at them .
Sent 5: To extract revenge , they kidnap Lizzie with the help of the embittered dog catchers , and take her to an abandoned shack , where they tie her to a post with a gun attached to a timer pointed at her head .
Sent 6: Plucky pup Luke follows the crooks , and is able to warn Fatty in time to perform the last-minute rescue , with the help of the Keystone Cops .
Sent 7: In the closing shot Fatty , Lizzie and Luke embrace in a joint kiss .
Question: Who expresses his love for Lizzie through a hole in the fence?
Incorrect Answer: luke.
| No.
| NIv2 | task057_multirc_classify_incorrect_answer | fs_opt |
You are given a statement written in Kannada. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
Ex Input:
Statement: <MASK>ಗಳು ಕಂಡುಬರುವ ಬೇರೆ ಸಾಂದ್ರ ವಲಯಗಳನ್ನೂ ಕ್ಷುದ್ರಗ್ರಹ ಹೊನಲು ಎಂದು ಕರೆಯಬಹುದಾದ್ದರಿಂದ, ಮಂಗಳ ಮತ್ತು ಗುರು ಗ್ರಹಗಳ ನಡುವೆ ಇರುವ ಈ ವಲಯವನ್ನು ಮುಖ್ಯ ಹೊನಲು ಎಂದು ಕರೆಯಲಾಗುತ್ತದೆ. ಹೆಸರು/ಸಂಖ್ಯೆ ಹೊಂದಿರುವ ಕ್ಷುದ್ರಗ್ರಹಗಳಲ್ಲಿ ೯೮.೫% ಕ್ಷುದ್ರಗ್ರಹಗಳು ಈ ವಲಯದಲ್ಲಿ ಇವೆ.
Option A: ಸೂರ್ಯ
Option B: ಚಂದ್ರ
Option C: ಗುರು
Option D: ಕ್ಷುದ್ರಗ್ರಹ
Ex Output:
ಕ್ಷುದ್ರಗ್ರಹ
Ex Input:
Statement: <MASK> 1738ರ ಡಿಸೆಂಬರ್ 31ರಂದು ಪ್ರಥಮ ಅರ್ಲ್ ಕಾರ್ನ್ವಾಲಿಸನ ಹಿರಿಯ ಮಗನಾಗಿ ಜನಿಸಿದ. 1757ರಲ್ಲಿ ಸೈನ್ಯವನ್ನು ಸೇರಿ ಜರ್ಮನಿಯಲ್ಲಿ ಏಳು ವರ್ಷಗಳ ಯುದ್ಧದಲ್ಲಿ ಭಾಗವಹಿಸಿದ. 1765ರ ಅನಂತರ ಕೆಲಕಾಲ ರಾಜಕಾರಣಕ್ಕಿಳಿದು ವಸಾಹತುಗಳ ತೆರಿಗೆಯ ನೀತಿಯನ್ನು ವಿರೋಧಿಸುತ್ತಿದ್ದ.
Option A: ಭಾರತ
Option B: ಜರ್ಮನಿ
Option C: ತಿರುವಾಂಕೂರು
Option D: ಲಂಡನಿನಲ್ಲಿ
Ex Output:
ಲಂಡನಿನಲ್ಲಿ
Ex Input:
Statement: ಅಗಸ್ಟ್ ೨೮, ೨೦೦೯ರಲ್ಲಿ <MASK> ವಿರುಧ್ಧ ನಡೆದ ಏಕೈಕ ಏಕದಿನ ಪಂದ್ಯದ ಮೂಲಕ ಇವರು ಅಂತರರಾಷ್ಟ್ರೀಯ ಕ್ರಿಕೆಟ್ ಜಗತ್ತಿಗೆ ಪಾದಾರ್ಪನೆ ಮಾಡಿದರು. ಅಗಸ್ಟ್ ೩೦, ೨೦೦೯ರಂದು ಮ್ಯಾಂಚೆಸ್ಟರ್ ನಲ್ಲಿ ಇಂಗ್ಲೆಂಡ್ ವಿರುದ್ಧ ನಡೆದ ಮೊದಲ ಟಿ-೨೦ ಪಂದ್ಯದಿಂದ ಅಂತರರಾಷ್ಟ್ರೀಯ ಟಿ-೨೦ ಕ್ರಿಕೆಟ್ ಗೆ ಪಾದಾರ್ಪನೆ ಮಾಡಿದರು. ಜುಲೈ ೧೩, ೨೦೧೦ ರಂದು ಲಾರ್ಡ್ಸ್ ನಲ್ಲಿ ಪಾಕಿಸ್ತಾನದ ವಿರುದ್ಧ ನಡೆದ ಮೊದಲನೇ ಟೆಸ್ಟ್ ಕ್ರಿಕೆಟ್ ಪಂದ್ಯದ ಮೂಲಕ ಇವರು ಅಂತರರಾಷ್ಟ್ರೀಯ ಟೆಸ್ಟ್ ಕ್ರಿಕೆಟ್ ನಲ್ಲಿ ಪಾದಾರ್ಪಣೆ ಮಾಡಿದರು.
Option A: ಸ್ಕಾಟ್ಲೆಂಡ್
Option B: ಪಾಕಿಸ್ತಾನದ
Option C: ಒರೆಗನ್
Option D: ಆಸ್ಟ್ರೇಲಿಯಾದ
Ex Output:
| ಸ್ಕಾಟ್ಲೆಂಡ್
| NIv2 | task948_wiki_cloze_kn_multiple_choice_question_answering | fs_opt |
You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.
Let me give you an example: Sentence1:i need a place to dine in the center thats expensive Sentence2: I have several options for you; do you prefer African, Asian, or British food? Sentence3: Any sort of food would be fine, as long as it is a bit expensive. Could I get the phone number for your recommendation?Question: Who has spoken the sentence 2? (A) User (B) System
The answer to this example can be: Answer: (A) User
Here is why: The sentence 1 is said by a user because the intent of it says that the information has to be gathered from the system
OK. solve this:
Sentence1: Booking was successful. The table will be reserved for 15 minutes. Reference number is : IMSY2GMJ . Is there anything else I can do for you today? Sentence2: Two people at 11:15 for 2 people. Sentence3: What day would you like to book your reservation? Sentence4: No, thank you Sentence5: Have a great day! Sentence6: I found one for you called restaurant alimentum. Would you like me to book it for you? Sentence7: Yes! Sentence8: I am looking for a local restaurant in the south that offers modern European cuisine Sentence9: For which day shall I book the table? Sentence10: Tuesday, please. Question: Who has spoken the sentence 8? (A) User (B) System
Answer: | Answer: (A) User | NIv2 | task638_multi_woz_classification | fs_opt |
You are given a sentence in English. Your job is to translate the English sentence into Arabic.
What does that even mean? | ما الذي يعنيه ذلك ؟ | NIv2 | task1220_ted_translation_en_ar | zs_opt |
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
One example is below.
Q: Head: PersonX plays a song<sep>Tail: to hear music.
A: Yes
Rationale: This is a good example. PersonX plays a song because PersonX wanted to hear music.
Q: Head: PersonX offer PersonY a position<sep>Tail: some help
A: | Yes | NIv2 | task1201_atomic_classification_xintent | fs_opt |
In this task, you are given a passage which has a question and the context. You have to generate an answer to the question based on the information present in the context.
Input: Consider Input: Context: The bradycardic agent zatebradine (UL-FS 49) reduces heart rate without negative inotropic or proarrhythmic effects. The aim was to experimentally characterize the influence of zatebradine on arterial baroreflex sensitivity (BRS) and heart rate variability (HRV) which are generally considered as estimates of vagal activity and have prognostic value in patients after myocardial infarction (MI).', 'Conscious rats were studied 3 days after left coronary artery ligation or sham-operation (SH). BRS was determined by linear regression analysis of RR-interval and mean arterial pressure changes evoked by intravenous (i.v.) injections of methoxamine and nitroprusside. HRV at rest was calculated from high-resolution electrocardiogram-recordings.', 'In MI-rats heart rate was similar to SH-rats, mean arterial pressure was lower and both BRS and HRV were markedly reduced. Zatebradine (0.5 mg/kg i.v.) reduced heart rate in MI-rats from 400 +/- 15 to 350 +/- 19 and in SH-rats from 390 +/- 19 to 324 +/- 6 beats/min without changing mean arterial pressure. Both BRS and HRV were restored in MI- and further increased in SH-rats by the drug. Effects of 0.05, 0.5 and 5 mg/kg zatebradine revealed a dose-dependency of heart rate reduction. The lowest dose enhanced reflex bradycardia despite little effect on heart rate and lack of effect on both reflex tachycardia and HRV.\Question: Does the bradycardic agent zatebradine enhance baroreflex sensitivity and heart rate variability in rats early after myocardial infarction?
Output: Both BRS and HRV are reduced in rats early after MI, indicating a depressed reflex and tonic vagal activity. Treatment with zatebradine enhances both BRS and HRV. These data suggest that the drug has both peripheral and central effects, leading to an increase of vagal control of heart rate.
Input: Consider Input: Context: Linitis plastica-type gastric carcinoma remains a disease with poor prognosis despite an aggressive surgical approach. Although a prominent pattern of disease failure is peritoneal carcinomatosis, some patients experience rapid disease progression without signs of the peritoneal disease.', 'Clinicopathologic data from 178 patients with linitis plastica-type gastric cancer operated on between 1991 and 2000 were analyzed. Survival stratified by curability of surgery, pN stage, and patterns of failure were evaluated by using the Kaplan-Meier method, and chi(2) test was used to evaluate correlation between the number of metastatic lymph nodes in terms of pN categories and the incidence of various patterns of metastasis and recurrence. Cox regression hazard model was used to identify independent prognostic factors.', 'R0 resection was performed only among 82 patients (46% of those who underwent laparotomy). Node metastasis was frequent with only 22 patients classified as pN0. Peritoneal carcinomatosis was observed in 131 patients and was the commonest pattern of recurrence. Bone metastasis, found in 13 patients, was associated with poor outcome, and its incidence was significantly correlated with the number of metastatic nodes. pT4 status and pN3 status were identified as significant independent prognostic determinants.\Question: Is the number of metastatic lymph nodes a significant risk factor for bone metastasis and poor outcome after surgery for linitis plastica-type gastric carcinoma?
Output: Treatment strategy for the linitis plastica should in general combine surgery with aggressive treatment directed toward peritoneal disease. However, patients with >16 metastatic nodes more often are associated with bone metastasis than those with modest nodal involvement and suffer from poor prognosis.
Input: Consider Input: Context: Aggressive periodontitis is characterized by rapid destruction of periodontal tissue caused by Aggregatibacter actinomycetemcomitans. Interleukin (IL)-1β is a proinflammatory cytokine, and its production is tightly regulated by inflammasome activation. Xylitol, an anticaries agent, is anti-inflammatory, but its effect on inflammasome activation has not been researched. This study investigates the effect of xylitol on inflammasome activation induced by A. actinomycetemcomitans.', 'The differentiated THP-1 macrophages were stimulated by A. actinomycetemcomitans with or without xylitol and the expressions of IL-1β and inflammasome components were detected by real time PCR, ELISA, confocal microscopy and Immunoblot analysis. The effects of xylitol on the adhesion and invasion of A. actinomycetemcomitans to cells were measured by viable cell count.', 'A. actinomycetemcomitans increased pro IL-1β synthesis and IL-1β secretion in a multiplicity of infection- and time-dependent manner. A. actinomycetemcomitans also stimulated caspase-1 activation. Among inflammasome components, apoptosis-associated speck-like protein containing a CARD (ASC) and absent in melanoma 2 (AIM2) proteins were upregulated by A. actinomycetemcomitans infection. When cells were pretreated with xylitol, proIL-1β and IL-1β production by A. actinomycetemcomitans infection was significantly decreased. Xylitol also inhibited ASC and AIM2 proteins and formation of ASC puncta. Furthermore, xylitol suppressed internalization of A. actinomycetemcomitans into differentiated THP-1 macrophages without affecting viability of A. actinomycetemcomitans within cells.\Question: Does aggregatibacter actinomycetemcomitans-Induced AIM2 Inflammasome Activation be Suppressed by Xylitol in Differentiated THP-1 Macrophages?
| Output: A. actinomycetemcomitans induced IL-1β production and AIM2 inflammasome activation. Xylitol inhibited these effects, possibly by suppressing internalization of A. actinomycetemcomitans into cells. Thus, this study proposes a mechanism for IL-1β production via inflammasome activation and discusses a possible use for xylitol in periodontal inflammation caused by A. actinomycetemcomitans.
| NIv2 | task849_pubmedqa_answer_generation | fs_opt |
In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.
Example Input: Urgent safety guidance for wagons carrying dangerous goods has been issued after a derailment in which 330,000 litres of diesel was spilled.
Example Output: Llangennech derailment: Safety guidance for dangerous goods
Example Input: More than £2m of government funding will go towards moving two GP surgeries in Shropshire into a nearby empty hospital ward, health bosses say.
Example Output: £2m 'to relocate two Whitchurch GP surgeries'
Example Input: Rihanna says that she she still loves ex-boyfriend Chris Brown despite him attacking her in 2009.
Example Output: | Rihanna 'still loves' Chris Brown after assault
| NIv2 | task1358_xlsum_title_generation | fs_opt |
In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.
Q: [['The Waterman', 'eatType', 'restaurant'], ['The Waterman', 'food', 'Chinese'], ['The Waterman', 'priceRange', 'less than £20'], ['The Waterman', 'customer rating', 'low'], ['The Waterman', 'area', 'riverside'], ['The Waterman', 'familyFriendly', 'no']]
A: Chinese _____ _____ is located in the riverside area and has a low customer rating. It has dishes costing less than 20 pounds and is not family friendly.
****
Q: [['Allen Park', 'CITY', 'Antrim'], ['Allen Park', 'HOME_TEAM', 'Chimney Corner']]
A: _____ in Antrim is home to the Chimney Corner football club.
****
Q: [['Cotto', 'eatType', 'coffee shop'], ['Cotto', 'priceRange', 'moderate'], ['Cotto', 'customer rating', '3 out of 5'], ['Cotto', 'area', 'city centre'], ['Cotto', 'near', 'The Portland Arms']]
A: | Situated near The Portland Arms on the riverfront, north of the City centre, the 3-star '_____' coffee shop serves a range of moderately-priced fast foods.
****
| NIv2 | task1407_dart_question_generation | fs_opt |
In this task, you are given a question and an answer. Answer "Yes" if the given answer correctly answers the question, otherwise answer "No".
[Q]: what is the name of the wizard of oz, Answer: The Wizard of Oz, known during his reign as The Great and Powerful Oz, is the epithet of Oscar Zoroaster Phadrig Isaac Norman Henkel Emmannuel Ambroise Diggs, a fictional character in the Land of Oz , created by American author L. Frank Baum .
[A]: Yes
[Q]: how many vehicles are registered in the us, Answer: Overall, there were an estimated 254.4 million registered passenger vehicles in the United States according to a 2007 DOT study.
[A]: Yes
[Q]: how old is the singer bob seger, Answer: As a locally successful Detroit-area artist, he performed and recorded as Bob Seger and the Last Heard and Bob Seger System throughout the 1960s.
[A]: | No
| NIv2 | task1294_wiki_qa_answer_verification | fs_opt |
You will be given a definition of a task first, then some input of the task.
Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.
What wasn't Chief Hendrick er uh William Johnson's role in British military?
Output: | What wasn't William Johnson's role in British military? | NIv2 | task1195_disflqa_disfluent_to_fluent_conversion | zs_opt |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.
[-83, 53, -48, 8]
Solution: [-80, 50, -50, 10]
Why? The output correctly rounds each integer in the input list to the nearest ten. So this is a good example.
New input: [-190, 891, -453]
Solution: | [-190, 890, -450] | NIv2 | task373_synthetic_round_tens_place | fs_opt |
In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions of the participants in the sentence and those affected by it. Is any of these emotions caused by the sentence? You should write your answer in the form " A >Causes> B". Try to use phrases and sentences from the story to compose your answer when possible. For the sentence describing the result, you must use the verb feel(s).
[EX Q]: story: Katelyn was sitting with her toddler. Their favorite song came on. The toddler wanted to sing. Katelyn began singing with him. The toddler loved it.
selected sentence: Katelyn began singing with him.
[EX A]: Katelyn sings with him >Causes> He feel(s) happy
[EX Q]: story: I turned on the television. My dog was sitting on the sofa. He started to watch the television. The dog show came on the television. My dog started barking at the dogs on television.
selected sentence: He started to watch the television.
[EX A]: My dog watched TV >Causes> My dog feel(s) included
[EX Q]: story: David had a bad toothache. He made an appointment with the dentist. The next week the dentist had to pull his tooth. David went home very sore to recover. The next day David felt much better without the pain.
selected sentence: The next week the dentist had to pull his tooth.
[EX A]: | The dentist has to pull his tooth >Causes> David feel(s) pained
| NIv2 | task749_glucose_reverse_cause_emotion_detection | fs_opt |
Definition: In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.
Input: Query: What are specific dangers of asbestos?
Clarification: do you want stores selling elliptical trainer
Output: | No | NIv2 | task227_clariq_classification | zs_opt |
Given the task definition, example input & output, solve the new input case.
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Example: ['hey', 'everybody', 'ivan', 'from', 'weights', 'and', 'biases', 'here', 'in', 'this', 'video', "i'd"]
Output: ['CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF']
This sentence is a good example since the input stream is a grammatically incorrect statement and the output labels correctly classify the words that were incorrect.
New input case for you: ['over', '2,000', 'years', 'ago', 'Euclid', 'showed', 'every', 'number', 'has', 'exactly', 'one', 'prime', 'factorization', 'which', 'we', 'can', 'think', 'of', 'as', 'a', 'secret', 'key', 'it', 'turns', 'out', 'that', 'prime', 'factorization', 'is', 'a', 'fundamentally', 'hard', 'problem', "let's", 'clarify', 'what', 'we', 'mean', 'by', 'easy', 'and', 'hard', 'by', 'introducing', "what's", 'called', 'time', 'complexity', 'we', 'have', 'all', 'multiplied', 'numbers', 'before', 'and', 'each', 'of', 'us', 'has', 'our', 'own', 'rules', 'for', 'doing', 'so', 'in', 'order', 'to', 'speed', 'things', 'up', 'if', 'we', 'program', 'a', 'computer', 'to', 'multiply', 'numbers', 'it', 'can', 'do', 'so', 'much', 'faster', 'than', 'any', 'human', 'can', 'here', 'is', 'a', 'graph', 'that', 'shows', 'the', 'time', 'required', 'for', 'a']
Output: | ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF'] | NIv2 | task1416_youtube_caption_corrections_incorrect_grammar_classification | fs_opt |
Teacher: You are given a set of queries separated by '
', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.
Teacher: Now, understand the problem? If you are still confused, see the following example:
How many miles is 43560 ?
What is the national currency of Albania ?
What is the status of the draft today in US ?
Where is the oil plug in a 2004 Harley ?
Solution: How many miles is 43560 ?
Reason: The output is from the list of given queries and it is not well structured and has grammatical errors when compared to other queries
Now, solve this instance: How do you clean polyester garden furniture ?
Best picture oscar 2001 ?
What is the name of the Russian space probe that visited haley 's comet ?
How can you seperate mixtures ?
Student: | Best picture oscar 2001 ? | NIv2 | task674_google_wellformed_query_sentence_generation | fs_opt |
Evaluate the similarity between them and classify them into classes from 0-5 as follows:
0 : The two sentences are completely dissimilar.
1 : The two sentences are not equivalent, but are on the same topic.
2 : The two sentences are not equivalent, but share some details.
3 : The two sentences are roughly equivalent, but some important information differs/missing.
4 : The two sentences are mostly equivalent, but some unimportant details differ.
5 : The two sentences are completely equivalent, as they mean the same thing.
Example input: Sentence 1: A plane is taking off. Sentence 2: An air plane is taking off.
Example output: 5
Example explanation: Here both statements are talking about the same thing hence it will be classified as a 5.
Q: Sentence 1: Israel's Peres urges return to peace talks Sentence 2: Israel's Peres calls for return to peace talks
A: | 5 | NIv2 | task1347_glue_sts-b_similarity_classification | fs_opt |
Instructions: You are given a short paragraph, a question and two choices to answer from. Choose the correct answer based on the paragraph and write the answer(not the key).
Input: Paragraph: Objects with greater mass have greater inertia.
Question: When something is very lightweight what does it need to move?
Choices: A)more inertia
B)less inertia
Output: | less inertia | NIv2 | task1731_quartz_question_answering | zs_opt |
In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
--------
Question: Hell no it was mad niggas tryna talk to me today at work 😭😭🤦🏽♀️
Answer: Yes
Question: All these bitches & niggas be Trippin offa what type of relationship me & duddy got like we not fuccing no more & we not dating.
Answer: Yes
Question: RT @HeidiL_RN: Fuck Islam you pigfucking trash troll. @ItsJustMe7o7 @MzKeriEvans @ctbauza
Answer: | Yes
| NIv2 | task609_sbic_potentially_offense_binary_classification | fs_opt |
In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command:
1. count: returns the number of rows in the view.
2. only: returns whether there is exactly one row in the view.
3. hop: returns the value under the header column of the row.
4. and: returns the boolean operation result of two arguments.
5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column.
6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column.
7. argmax/argmin: returns the row with the max/min value in header column.
8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column.
9. eq/not_eq: returns if the two arguments are equal.
10. round_eq: returns if the two arguments are roughly equal under certain tolerance.
11. greater/less: returns if the first argument is greater/less than the second argument.
12. diff: returns the difference between two arguments.
13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument.
14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument.
15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument.
16. filter_all: returns the view itself for the case of describing the whole table
17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument.
18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument.
19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument.
20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument.
21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument.
22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.
Q: select the rows whose method record fuzzily matches to draw . there is only one such row in the table . the res record of this unqiue row is draw .
A: | and { only { filter_eq { all_rows ; method ; draw } } ; eq { hop { filter_eq { all_rows ; method ; draw } ; res } ; draw } } | NIv2 | task210_logic2text_structured_text_generation | zs_opt |
Detailed Instructions: In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.
See one example below:
Problem: Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in existing GPUs. MPT is typically used in combination with a technique called loss scaling, that works by scaling up the loss value up before the start of backpropagation in order to minimize the impact of numerical underflow on training. Unfortunately, existing methods make this loss scale value a hyperparameter that needs to be tuned per-model, and a single scale cannot be adapted to different layers at different training stages. We introduce a loss scaling-based training method called adaptive loss scaling that makes MPT easier and more practical to use, by removing the need to tune a model-specific loss scale hyperparameter. We achieve this by introducing layer-wise loss scale values which are automatically computed during training to deal with underflow more effectively than existing methods. We present experimental results on a variety of networks and tasks that show our approach can shorten the time to convergence and improve accuracy, compared with using the existing state-of-the-art MPT and single-precision floating point.
Solution: We devise adaptive loss scaling to improve mixed precision training that surpass the state-of-the-art results.
Explanation: The abstract focusses on designing an adaptive loss scaling method, hence the generated output is correct.
Problem: Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end
deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is
the large number of out-of-vocabulary words. In this paper we proposed an algorithm which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of next utterance selection, the proposed method has demonstrated a significant performance improvement against original ESIM and the new model has achieved state-of-the-art results on both Ubuntu dialogue corpus and Douban conversation corpus. In addition, we investigated the performance impact of end-of-utterance and end-of-turn token tags.
Solution: | Combine information between pre-built word embedding and task-specific word representation to address out-of-vocabulary issue | NIv2 | task668_extreme_abstract_summarization | fs_opt |
TASK DEFINITION: You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.
PROBLEM: Sentence1: I would prefer one of the expensive places. Need to impress my guests, you know? Sentence2: I see one moderately priced Indian restaurant in that area, and several expensive ones. Do you have a preference? Sentence3: Actually, I would like to book the hotel for 6 people for 4 nights starting on Sunday. Sentence4: I want an expensive place to stay in the west side. Sentence5: Okay, the phone number is 01480446000 for your convenience. Is there anything else I can help you with? Sentence6: There are three expensive Indian Restaurants in that area. Can I recommend Tandoori Palace? Sentence7: Thank you, you have a good day! Sentence8: I don't really need internet, but that sounds like everything else I want. Yes, I'd like you to book it. Sentence9: Yes, is 3 nights possible? Could I also please have a reference number? Sentence10: I was not able to reserve a table for you at that time. Is there a different day or time slot that you would like? Sentence11: Booking was not possible. Would you like to try a shorter stay, fewer rooms, or another day? Sentence12: Great! I have a table for 6 people at 11:30 onSundar at Tandoori Palace, Reference Number 3BMGPAN3 . Is there anything else I can do for you? Sentence13: I will hold off on the booking today I think I have all I need Sentence14: No thank you, that is all I needed! Sentence15: Thank you. I would like to make reservations for my party to have dinner one night near the hotel. We would like to go to a restaurant that serves Indian food, if possible. Sentence16: Great, the booking was successful. Your reference number is HJHE475H . Is there anything else I can help you with? Sentence17: OK, what is your arrival date, number of nights, and number of people in your party? Sentence18: Yes, that sounds good. Please book it for the same 6 people at 12:30 on Sunday. Sentence19: The Huntingdon Marriott Hotel is an expensive, 4-star hotel in the west that offers free internet and parking. Would you like me to book this for you? Sentence20: Yes, how about 11:30 instead? Please send reference number for the booking. Question: Who has spoken the sentence 1? (A) User (B) System
SOLUTION: Answer: (B) System
PROBLEM: Sentence1: What is your departure point? Sentence2: What time do you need to leave by? Sentence3: I am looking for a train to cambridge. I would like something on sunday to arrive by 18:30 Sentence4: I just want to get there at or shortly before 18:30. Sentence5: I'd like to recommend whipple museum of the history of science, at free school lane. Admission is free. Sentence6: Yes it is their full address and the postcode is cb23rh and their telephone number is 01223330906. May I help you with anything else today? Sentence7: Thank you. That is all that I need. Sentence8: i place want a place to go in the centre Sentence9: I found the perfect train! TR7771 will get you there at 18:24. Would you like me to book this for you? Sentence10: Ok, your booking is complete for 6 people. The cost is 79.19 GBP, payable at the station. The reference number is 8W0OSFM6 . Sentence11: I would like a museum in the centre please. Sentence12: What are you into? Do you like theatre? Museums? We have plenty of attractions in the centre and if you tell me what you enjoy I can recommend one Sentence13: My departure will be from Cambridge. Sentence14: Okay. Glad I could be of help. Sentence15: Is that the full address for the museum? Free School Lane? Sentence16: I need to go to Peterborough. Sentence17: Yes, please book me for 6 people. My birdwatching club is taking a trip together. Sentence18: And what is your destination city? Question: Who has spoken the sentence 6? (A) User (B) System
SOLUTION: Answer: (A) User
PROBLEM: Sentence1: Booking was successful. The table will be reserved for 15 minutes. Reference number is : IMSY2GMJ . Is there anything else I can do for you today? Sentence2: Two people at 11:15 for 2 people. Sentence3: What day would you like to book your reservation? Sentence4: No, thank you Sentence5: Have a great day! Sentence6: I found one for you called restaurant alimentum. Would you like me to book it for you? Sentence7: Yes! Sentence8: I am looking for a local restaurant in the south that offers modern European cuisine Sentence9: For which day shall I book the table? Sentence10: Tuesday, please. Question: Who has spoken the sentence 8? (A) User (B) System
SOLUTION: | Answer: (A) User
| NIv2 | task638_multi_woz_classification | fs_opt |
You are given a sentence in Polish. Your job is to translate the Polish sentence into Japanese.
Example: Wszystko jest robione pomiędzy żebrami.
Example solution: 全て肋骨の間から行うのです
Example explanation: The Polish sentence is correctly translated into Japanese, because the meaning is preserved.
Problem: W istocie, jestem maniakiem danych.
| Solution: データおたくなんです | NIv2 | task1257_ted_translation_pl_ja | fs_opt |
instruction:
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
question:
Head: PersonX plays PersonX's best<sep>Tail: to do well
answer:
Yes
question:
Head: PersonX affords every ___<sep>Tail: to spoil their fiance
answer:
No
question:
Head: PersonX offer PersonY a position<sep>Tail: some help
answer:
| Yes
| NIv2 | task1201_atomic_classification_xintent | fs_opt |
Given the task definition and input, reply with output. In this task you are given a tweet that contains some form of irony. You must classify the type of irony the tweet has. Label the tweets ("polarity","situational","other") based on the irony they have. Situational irony happens when a situation fails to meet some expectations, Label these instances as "situational". polarity irony happens when irony is achieved by inverting the intended sentence, Label these instances as "polarity". There are other kinds of ironies that are neither polarity nor situational, Label these instances as "other". Note that URLs in the text have been replaced with [Link].
@drapermark37 @susanbnj We must be tolerant and embrace the peaceful Islamic faith, Muslims are our peaceful brothers
| polarity | NIv2 | task387_semeval_2018_task3_irony_classification | zs_opt |
Teacher:In this task, you are given an input list A. If the count of numbers is more than that of alphabets in the list, answer 'Numbers Win'. If the count of alphabets is more than that of numbers in the list, answer 'Alphabets Win'. If the count of numbers is same as that of alphabets in the list, answer 'Numbers and Alphabets are Tied'.
Teacher: Now, understand the problem? Solve this instance: ['2797', '4359', '3277', '7797', 'P', '7485', '2507', 'F', '9119', '5931', 'D', 'x', 'S', '8813', 'v']
Student: | Numbers Win | NIv2 | task523_find_if_numbers_or_alphabets_are_more_in_list | zs_opt |
You are given a sentence in Italian. Your job is to translate the Italian sentence into Portugese.
One example: Ora, lungo il percorso, George segnala che la sua tecnologia, la tecnologia della biologia sintetica, sta accelerando molto più velocemente del tasso previsto dalla Legge di Moore.
Solution is here: Ao longo do livro, George chama a atenção de que a sua tecnologia, a tecnologia da biologia sintética, está atualmente a acelerar a uma taxa 4 vezes superior à Lei de Moore.
Explanation: The Italian sentence is correctly translated into Portugese, because the meaning is preserved.
Now, solve this: E 'l'unica minaccia, l'unica influenza che la barriera ha dovuto affrontare.
Solution: | É a única ameaça, a única influência com a qual o recife teve de lidar. | NIv2 | task1255_ted_translation_it_pt | fs_opt |
Q: You are given a sentence in Polish. Your job is to translate the Polish sentence into Japanese.
Ten kamień pochodzi z Gona w Etopii. Identycznych używali nasi afrykańscy przodkowie dwa i pół miliona lat temu.
A: | カンジの石はエチオピアのゴナ産です 250万年前アフリカの祖先が使った石と同じです | NIv2 | task1257_ted_translation_pl_ja | zs_opt |
In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.
[574, -317, 666, -691, 556, 826, 360]
[570, -320, 670, -690, 560, 830, 360]
[-533, -200, 607, 657, 979, -377, 102, 529]
[-530, -200, 610, 660, 980, -380, 100, 530]
[-190, 891, -453]
| [-190, 890, -450]
| NIv2 | task373_synthetic_round_tens_place | fs_opt |
Part 1. Definition
Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc.
Part 2. Example
Sentence: Jack played basketball after school, after which he was very tired.
Question: How long did Jack play basketball?
Category: Event Duration.
Answer: Yes.
Explanation: The question asks about the duration of playing basketball, therefore it's a "event duration" question.
Part 3. Exercise
Sentence: In a matter of 48 hours, Alexander II planned to release his plan for the duma to the Russian people.
Question: What did Alexander II do before releasing his plan?
Category: Event Ordering.
Answer: | Yes. | NIv2 | task019_mctaco_temporal_reasoning_category | fs_opt |
You are given a statement written in Hindi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
Let me give you an example: Statement: सिग्नेचर केल्विन क्लेन अंडरवियर बुटीक, ब्यूनस आयर्स, टोरंटो, मेक्सिको सिटी, <MASK>, ग्लासगो, मेलबोर्न, हांगकांग, लंदन, मैनचेस्टर, न्यूयॉर्क शहर, शंघाई, फ्रैंकफर्ट एम् मेन, सिंगापुर में देखे जा सकते हैं। केल्विन क्लेन अंडरवियर, कार्डिफ़ के सेंट डेविड शॉपिंग सेंटर में भी 2010 में क्रिसमस से पहले एक दुकान खोलने जा रहा है।
Option A: मैनचेस्टर
Option B: मैनचेस्टर
Option C: एडिनबर्ग
Option D: मेलबोर्न
The answer to this example can be: एडिनबर्ग
Here is why: The most suitable word from the given options to replace the <MASK> token is एडिनबर्ग as the rest places have already been stated in the statement .
OK. solve this:
Statement: देश में रावी और ब्यास नदी जल विवाद काफी पुराना है। यह <MASK> के दो राज्यों पंजाब (भारत) और हरियाणा के बीच रावी और ब्यास नदियों के अतरिक्त पानी के बंटवारे को लेकर हैं। मुकदमे सालों से अदालतों में हैं।
Option A: हिमाचल
Option B: हरियाणा
Option C: भारत
Option D: आयरलैंड
Answer: | भारत | NIv2 | task947_wiki_cloze_hi_multiple_choice_question_answering | fs_opt |
Detailed Instructions: Given a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.
Problem:Velma Kelly and Billy Flynn are two of the leading characters in which 2002 musical?
Solution: | film | NIv2 | task900_freebase_qa_category_classification | zs_opt |
In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb
One example is below.
Q: What is the part-of-speech tag of the word "the" in the following question: Who were the builders of the mosque in Herat with fire temples ?
A: DT
Rationale: This is a good example. POS tag of "the" is DT.
Q: What is the part-of-speech tag of the word "by" in the following question: When was the boat commanded by the oldest korvettenkapitän launched ?
A: | IN | NIv2 | task382_hybridqa_answer_generation | fs_opt |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
In this task, you need to count the number of words in a sentence that start with the given letter. Answer with numbers and not words.
Sentence: 'a hot dog in a bun with ketchup on a plate with french fries'. How many words start with the letter 'a' in the sentence.
Solution: 3
Why? The word 'a' is the only word that starts with 'a'. This sentence has 3 occurrences of the word 'a'. So, the answer is 3.
New input: Sentence: 'a male in a wet suit surfing on a black and white board'. How many words start with the letter 'a' in the sentence.
Solution: | 4 | NIv2 | task162_count_words_starting_with_letter | fs_opt |
Detailed Instructions: In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.
Q: claim: Animal testing should be banned.
perspective: When research is done on animals, it causes them severe harm.
A: | support | NIv2 | task738_perspectrum_classification | zs_opt |
Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].
Ex Input:
['when', 'you', 'ask', 'composers', 'who', 'their', 'favorite', 'composer', 'is', 'you', 'get', 'unusual', 'answers', 'regarde', 'Strauss', 'for', 'example', 'who', 'wrote', 'Elektra', 'and', 'Rosenkavalier', 'and', '', 'great', 'tone', 'poems', '-', 'Lauren', 'Spiegel', 'xerath', 'rooster', 'his', 'favorite', 'composer', 'was', 'Mozart', 'Tchaikovsky', 'this', 'great', 'Romantic', 'who', 'wrote', 'music', 'that', 'was', 'so', 'passionate', 'and', 'so', 'full', 'of', 'drama', 'his', 'favorite', 'composer', 'was', 'Mozart', 'you', "wouldn't", 'think', 'that', 'and', 'they', 'used', 'them', 'a', 'lot', 'of', 'miss', 'Strauss', 'for', 'example', 'conducted', 'Mozart', 'a', 'lot', 'Tchaikovsky', 'actually', 'wrote', 'a', 'suite', 'called', 'more', 'Tatiana', 'where', 'he', 'took', 'Mozart', 'pieces', 'and', 'orchestrated', 'them', 'and', 'in', 'in', 'the', 'list', 'version', 'which']
Ex Output:
['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF']
Ex Input:
['so', 'in', 'the', 'last', 'video', 'I', 'talked', 'about', 'three-dimensional', 'vector', 'fields', 'and', 'I', 'finish', 'things', 'off', 'with', 'this', 'sort', 'of', 'identity', 'function', 'example', 'where', 'at', 'an', 'input', 'input', 'point', 'XYZ', 'the', 'output', 'vector', 'is', 'also', 'XYZ', 'and', 'here', 'I', 'want', 'to', 'go', 'through', 'a', 'slightly', 'more', 'intricate', 'example', 'so', "I'll", 'go', 'ahead', 'and', 'get', 'rid', 'of', 'this', 'vector', 'field', 'and', 'in', 'this', 'example', 'the', 'X', 'component', 'of', 'the', 'output', 'will', 'be', 'Y', 'times', 'Z', 'the', 'Y', 'component', 'of', 'the', 'output', 'will', 'be', 'x', 'times', 'Z', 'and', 'the', 'Z', 'component', 'of', 'the', 'output', 'will', 'be', 'x', 'times', 'y', 'so', "we'll", 'just']
Ex Output:
['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'STEM_BASED_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF']
Ex Input:
['over', '2,000', 'years', 'ago', 'Euclid', 'showed', 'every', 'number', 'has', 'exactly', 'one', 'prime', 'factorization', 'which', 'we', 'can', 'think', 'of', 'as', 'a', 'secret', 'key', 'it', 'turns', 'out', 'that', 'prime', 'factorization', 'is', 'a', 'fundamentally', 'hard', 'problem', "let's", 'clarify', 'what', 'we', 'mean', 'by', 'easy', 'and', 'hard', 'by', 'introducing', "what's", 'called', 'time', 'complexity', 'we', 'have', 'all', 'multiplied', 'numbers', 'before', 'and', 'each', 'of', 'us', 'has', 'our', 'own', 'rules', 'for', 'doing', 'so', 'in', 'order', 'to', 'speed', 'things', 'up', 'if', 'we', 'program', 'a', 'computer', 'to', 'multiply', 'numbers', 'it', 'can', 'do', 'so', 'much', 'faster', 'than', 'any', 'human', 'can', 'here', 'is', 'a', 'graph', 'that', 'shows', 'the', 'time', 'required', 'for', 'a']
Ex Output:
| ['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']
| NIv2 | task1416_youtube_caption_corrections_incorrect_grammar_classification | fs_opt |
In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by two, if the element is odd you should multiply by three then add one. The output should be a list of integers that is the result of applying that logic to the input list.
[199, 84] | [598, 42] | NIv2 | task206_collatz_conjecture | zs_opt |
You are given a set of queries separated by '
', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.
Input: Consider Input: How does a yam taste like ?
What is the salary for a piano musician ?
How do you verify your account on aqworlds ?
Why is dope called dope ?
Output: How does a yam taste like ?
Input: Consider Input: Who discovered the element Antimony and when ?
How many known elements are there at this time ?
What is the history on plain indians ?
What continent is Curacao located on ?
Output: What is the history on plain indians ?
Input: Consider Input: How do you clean polyester garden furniture ?
Best picture oscar 2001 ?
What is the name of the Russian space probe that visited haley 's comet ?
How can you seperate mixtures ?
| Output: Best picture oscar 2001 ?
| NIv2 | task674_google_wellformed_query_sentence_generation | fs_opt |
Given the task definition, example input & output, solve the new input case.
In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.
Example: [[7, -3, -3, 11], [-6, -6, -5, 2], [-8, 4, -3]]
Output: [0, 72, -32]
The first inner list has no even integers, so the first number in the output is 0. The second list has -6, -6, 2 for even integers so the second output is 72. The third list has -8, 4 as even numbers so the third output is -32. This is a good example.
New input case for you: [[9, -30, -31, -47], [14, -2], [-23, 45, 11], [9, 25, 39, 31, -14], [-34, 48, -12, -5, -32], [-40, -25, -23, -6, -28], [32, 45, 42, 42], [-32, 6, -17, 44, 39], [11, 29], [44, -31, -39], [-32, 6], [-39, -10]]
Output: | [-30, -28, 0, -14, -626688, -6720, 56448, -8448, 0, 44, -192, -10] | NIv2 | task851_synthetic_multiply_evens | fs_opt |
Teacher: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.
Teacher: Now, understand the problem? If you are still confused, see the following example:
In one work this author details the life of a tomb-maker who makes extra money by playing the organ at an insane asylum, while another of his novels sees Swartz give a refugee proper documentation only after he tells him his life story in the title Portuguese city. In addition to The Black Obelisk and The Night in Lisbon, he also wrote about Robert and Otto selling their auto workshop and visiting Patrice in a Swiss tuberculosis sanatorium in his novel The Three Comrades, while the turbulent life of the German surgeon Ravic is told in The Arch of Triumph. Another of his novels, The Road Back, is thought to be a sequel to his most famous book, in which the patriotic teacher Kantorek convinces Paul Bumer and his friends to join the Germany Army during World War I. For 10 points, name this German author who wrote All Quiet on the Western Front.
Solution: Literature
Reason: The text is talking about an author and their works, so it belongs to theliterature category.
Now, solve this instance: This man and Blatt name a method for inducing cognitive dissonance by asking questions and then letting the subject spontaneously formulate a response. He used the term "Hierarchic Integration" to describe one of his theories, which relies on a process of conflict resolution called "justice operation." This psychologist proposed a thought experiment in which a man breaks into adrug store to steal for his sick wife. His best-known work was criticized for only examining male subjects in the book In A Different Voice by Carol Gilligan. That work outlines a theory dividing development into three levels: pre-conventional, conventional, and post-conventional. For 10 points, name this psychologist who outlined a six stage theory of moral development.
Student: | Social Science | NIv2 | task521_trivia_question_classification | fs_opt |
You will be given a definition of a task first, then some input of the task.
In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about "doctors", you can talk about "health" or "diagnosis", but don't mention "aliens". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: "She likes cakes." is changed to "She doesn't like cakes."
Beginning: The dog was playing with his bone. Middle: The dog put down his bone and started looking for his owner. Ending: The dog went inside and got a treat from his owner.
Output: | The cat put down his mouse and started looking for another. | NIv2 | task068_abductivenli_incorrect_answer_generation | zs_opt |
You are given a sentence in Polish. Your job is to translate the Polish sentence into Galician.
Example input: Dzisiaj, w Szwecji i innych bogatych krajach ludzie używają mnóstwo najróżniejszych urządzeń.
Example output: Hoxe, en Suecia e outros países ricos, a xente usa moitas máquinas diferentes.
Example explanation: The Polish sentence is correctly translated into Galician, because the meaning is preserved.
Q: Niektóre wyglądają jak te, w których mieszkałem jako student.
A: | Algúns parécense a apartamentos nos que vivín cando era estudante. | NIv2 | task1261_ted_translation_pl_gl | fs_opt |
Definition: In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_) and their corresponding answer. The sentence pair should look similar, and should be about two related but different objects; for example "trophy" and "suitcase". Additionally, the two sentences must be different in terms of trigger words (e.g., "small" and "big") which express contrasting properties about the two objects. The answer must not be associated with the trigger word; instead, it should depend on the context present in twin sentences. Also, the answers should not be ambiguous. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals and proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style or phrase in twin sentences. E.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that ObjectX and Y have the same number e.g. when ObjectX is singular, ObjectY must be singular, too. The two objects (ObjectX & ObjectY) should be used ONCE in each sentence. Here is a list of contrastive words that may be used as trigger words. You should create more such trigger words and use them in your twin sentences.
| Attribute | triggerword | contrastive triggerword |
| age | old | new |
| altitude | low | high |
| area | small | vast |
| brightness | dark | light |
| clarity | obscure | clear |
| cleanness | dirty | clean |
| complexity | simple | complex |
| cost | cheap | expensive |
| density | sparse | dense |
| depth | shallow | deep |
| distance | near | far |
| electric conductivity | low | high |
| flexibility | rigid | flexible |
| granularity | fine | coarse |
| hardness | soft | hard |
| length | short | long |
| magnitude | small | large |
| mass | small | large |
| odor | weak | strong |
| pressure | low | high |
| resistance | low | high |
| shape | round | sharp |
| shape | flat | spiky |
| size | small | large |
| sound | quiet | loud |
| sound pitch | low | high |
| speed | slow | fast |
| stability | unstable | stable |
| strength | weak | strong |
| temperature | low | high |
| texture | smooth | rough |
| thermal conductivity | low | high |
| thickness | thin | thick |
| volume | small | large |
| weight | light | heavy |
| width | narrow | wide |
| location | in | out |
| location | up | down |
| location | above | below |
| location | on | off |
| location | to | from |
Input: Context Word: ratio.
Output: | Sentence 1: The ratio for the mixture was ruined due to the fact that the _ was not proportional.
Answer1: ratio.
Sentence 2: The ratio for the mixture was ruined due to the fact that the _ was disproportionate.
Answer2: mixture. | NIv2 | task029_winogrande_full_object | zs_opt |
Detailed Instructions: You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Farsi.
See one example below:
Problem: 私たちはただひたすら歌い続けましたすると驚くことに信頼が芽生え友情が花開いたのです
Solution: ما آواز خوندیم ، و خوندیم ، آواز خونديم ، و بطور شگفت انگیزی اعتماد جدید رشد کرد ، و درواقع دوستی شکوفه زد.
Explanation: The Japanese sentence is correctly translated into Farsi, because the meaning is preserved.
Problem: タイプⅡのミスは偽陰性です
Solution: | خطای نوع دوم ما منفی نادرست است. | NIv2 | task1098_ted_translation_ja_fa | fs_opt |
You are given a math word problem and you are supposed to apply multiple mathematical operators like addition, subtraction, multiplication or division on the numbers embedded in the text to answer the following question and then only report the final numerical answer.
Example: For the school bake sale Bianca made 14 cupcakes . If she sold 6 of them and then made 17 more , how many cupcakes would she have ?
Example solution: 25
Example explanation: Total cupcakes she would have = baked - sold = 14 -6 + 17 = 25
Problem: There are 43 pencils in the drawer and 19 pencils on the desk . Dan placed 16 pencils on the desk . How many pencils are now there in total ?
| Solution: 78 | NIv2 | task867_mawps_multiop_question_answering | fs_opt |
You are given a statement written in Telugu. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
One example: Statement: ఇది మండల కేంద్రమైన నాతవరం నుండి 8 కి. మీ. దూరం లోను, సమీప పట్టణమైన <MASK> నుండి 26 కి. మీ. దూరంలోనూ ఉంది. 2011 భారత జనగణన గణాంకాల ప్రకారం ఈ గ్రామం 198 ఇళ్లతో, 651 జనాభాతో 246 హెక్టార్లలో విస్తరించి ఉంది. గ్రామంలో మగవారి సంఖ్య 323, ఆడవారి సంఖ్య 328. షెడ్యూల్డ్ కులాల సంఖ్య 16 కాగా షెడ్యూల్డ్ తెగల సంఖ్య 69. గ్రామం యొక్క జనగణన లొకేషన్ కోడ్ 585743.పిన్ కోడ్: 531115.
Option A: నాతవరం
Option B: కొనియాల్
Option C: తుని
Option D: నర్సీపట్నం
Solution is here: తుని
Explanation: The most suitable word from the given options to replace the <MASK> token is తుని, as the town Tuni matches all the demographic data mentioned in the statement while the other towns don't .
Now, solve this: Statement: ఇది మండల కేంద్రమైన వరరామచంద్రపురం నుండి 21 కి. మీ. దూరం లోను, సమీప పట్టణమైన <MASK> నుండి 116 కి. మీ. దూరంలోనూ ఉంది. 2011 భారత జనగణన గణాంకాల ప్రకారం ఈ గ్రామం 147 ఇళ్లతో, 418 జనాభాతో 202 హెక్టార్లలో విస్తరించి ఉంది. గ్రామంలో మగవారి సంఖ్య 191, ఆడవారి సంఖ్య 227. షెడ్యూల్డ్ కులాల సంఖ్య 9 కాగా షెడ్యూల్డ్ తెగల సంఖ్య 354. గ్రామం యొక్క జనగణన లొకేషన్ కోడ్ 579238.పిన్ కోడ్: 507135.
Option A: జహానాబాద్
Option B: పాల్వంచ
Option C: ఖమ్మం
Option D: కూనవరంలోను
Solution: | పాల్వంచ | NIv2 | task954_wiki_cloze_te_multiple_choice_question_answering | fs_opt |
Evaluate the similarity between them and classify them into classes from 0-5 as follows:
0 : The two sentences are completely dissimilar.
1 : The two sentences are not equivalent, but are on the same topic.
2 : The two sentences are not equivalent, but share some details.
3 : The two sentences are roughly equivalent, but some important information differs/missing.
4 : The two sentences are mostly equivalent, but some unimportant details differ.
5 : The two sentences are completely equivalent, as they mean the same thing.
Example Input: Sentence 1: Operation Chaos is merely people voting. Sentence 2: Chaos is merely people voting.
Example Output: 4
Example Input: Sentence 1: Two people are riding a motorcycle. Sentence 2: Two people are riding a bike.
Example Output: 2
Example Input: Sentence 1: Israel's Peres urges return to peace talks Sentence 2: Israel's Peres calls for return to peace talks
Example Output: | 5
| NIv2 | task1347_glue_sts-b_similarity_classification | fs_opt |
Instructions: In this task, you are given a post in Spanish from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer "hateful" or "Non-hateful". Note that the URLs in the text have been replaced with [Link].
Input: Post: @chochos Pero tú eres puta del PRI
Output: | Hateful | NIv2 | task334_hateeval_classification_hate_es | zs_opt |
You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'.
Q: Person1: I have a suggestion . Why don't we go to a ETV and sing ?
Person2:A ETV ? Are you serious ? ETV ?
Person1: Yes , why not ? Don ’ t you like ETV ?
Person2:I don't know . I never went to one .
Person1: Never ? Really ? I'm surprised .
Person2:Many Americans have never gone to a ETV . It ’ s not an American thing to do .
Person1: But there are a lot of Kts in this town . There's one just two blocks from here .
Person2:OK , let's go .
A: | informal | NIv2 | task1533_daily_dialog_formal_classification | zs_opt |
Part 1. Definition
You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with "Description", "Entity", "Abbreviation", "Person", "Quantity", and "Location".
Part 2. Example
What's the most common name in nursery rhymes ?
Answer: Person
Explanation: This question is about people's names. So, the output should be "Person".
Part 3. Exercise
What is the price for tuberculosis drugs ?
Answer: | Quantity | NIv2 | task1289_trec_classification | fs_opt |
In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.
Q: We show that information about whether a neural network's output will be correct or incorrect is present in the outputs of the network's intermediate layers. To demonstrate this effect, we train a new "meta" network to predict from either the final output of the underlying "base" network or the output of one of the base network's intermediate layers whether the base network will be correct or incorrect for a particular input. We find that, over a wide range of tasks and base networks, the meta network can achieve accuracies ranging from 65% - 85% in making this determination.
A: Information about whether a neural network's output will be correct or incorrect is somewhat present in the outputs of the network's intermediate layers.
****
Q: We propose a "plan online and learn offline" framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local trajectory optimization can cope with approximation errors in the value function, and can stabilize and accelerate value function learning. Conversely, we also study how approximate value functions can help reduce the planning horizon and allow for better policies beyond local solutions. Finally, we also demonstrate how trajectory optimization can be used to perform temporally coordinated exploration in conjunction with estimating uncertainty in value function approximation. This exploration is critical for fast and stable learning of the value function. Combining these components enable solutions to complex control tasks, like humanoid locomotion and dexterous in-hand manipulation, in the equivalent of a few minutes of experience in the real world.
A: We propose a framework that incorporates planning for efficient exploration and learning in complex environments.
****
Q: Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end
deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is
the large number of out-of-vocabulary words. In this paper we proposed an algorithm which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of next utterance selection, the proposed method has demonstrated a significant performance improvement against original ESIM and the new model has achieved state-of-the-art results on both Ubuntu dialogue corpus and Douban conversation corpus. In addition, we investigated the performance impact of end-of-utterance and end-of-turn token tags.
A: | Combine information between pre-built word embedding and task-specific word representation to address out-of-vocabulary issue
****
| NIv2 | task668_extreme_abstract_summarization | fs_opt |
Given the task definition and input, reply with output. In this task, you are given a context paragraph, a question based on that and corresponding answer of a question. Your task is to generate supporting fact/knowledge from context paragraph which helps in answering a given question.
"Can I Be Him" is a song performed by British singer and songwriter James Arthur. The song was released as a digital download on 15 April 2017 in the United Kingdom by Columbia Records as the third single from his second studio album "Back from the Edge" (2016). The song has peaked at number 67 on the Scottish Singles Chart. Question: What season of The X Factor did the singer of Can I Be Him win? Answer: ninth
| Can I Be Him is a song performed by British singer and songwriter James Arthur. | NIv2 | task192_hotpotqa_sentence_generation | zs_opt |
You are given a sentence in Polish. Your job is to translate the Polish sentence into Japanese.
[Q]: (Śmiech) Mój tata miał warsztat samochodowy.
[A]: (笑) 父は自動車修理工場を持っていました
[Q]: Biodegradacja plastiku zajmuje od setek do tysięcy lat.
[A]: プラスチックの生分解には何百年何千年とかかります
[Q]: W istocie, jestem maniakiem danych.
[A]: | データおたくなんです
| NIv2 | task1257_ted_translation_pl_ja | fs_opt |
Teacher:In this task, you're given a context, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both context and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the context or linked information.
Teacher: Now, understand the problem? Solve this instance: Context: For her third movie Link Information: ast.- Shah Rukh Khan as Rahul Khanna, A popular student at St. Xavier's College and Anjali Sharma's best friend. He falls in love with Tina Malhotra and marries her, after which they have a baby girl who is named Anjali. He does not realise his love for Anjali Sharma until he meets her again.
- Kajol as Anjali Sharma, A fun-loving tomboy in college and the best friend of Rahul. Over time, she becomes friends with Tina but also falls in love with Rahul. Once she realises that Rahul and Tina love each other, she is devastated and decides to leave the college.
- Rani Mukerji as Tina Khanna (née Malhotra), The daughter of the principal of St. Xavier's, who is a transfer student from Oxford University. Elegant and sophisticated, she is described as the most beautiful girl in college. She falls in love with Rahul and marries him. The couple has a daughter, but Tina but has always felt guilty about coming between Anjali Sharma and Rahul. She passes away after giving birth, and her last wish is for Rahul to name their child Anjali.
- Salman Khan as Aman Mehra, Anjali Sharma's ex-fiancé.
- Sana Saeed as Anjali Khanna, Named after Anjali Sharma by Tina, she is both Rahul and Tina's daughter. She is independent and fun-loving, and her character mirrors that of Anjali Sharma during the latter's college days. She plays matchmaker between her father and his old college best friend, Anjali Sharma.
- Farida Jalal as Mrs. Savitha Khanna: Rahul's widowed mother. She is very religious and patriotic and supports her granddaughter Anjali in her quest to reunite her father and his best friend. She also constantly irritates Col. Almeida at Camp Sunshine with her patriotism.
- Anupam Kher as Principal Malhotra: Tina's father and the principal of St. Xavier's College. He is slightly infatuated with Ms. Briganza.
- Archana Puran Singh as Ms. Briganza: An English teacher at St. Xavier's. She constantly flirts with Principal Malhotra.
- Reema Lagoo as Mrs. Sharma: She is Anjali Sharma's mother and has doubts about her daughter's desires to marry Aman.
- Himani Shivpuri as Rifat Bi: The St. Xavier's girls' hostel matron. She acts as a motherly figure toward Anjali Sharma.
- Johnny Lever as Col. Almeida: The half-British manager of Camp Sunshine. He is a staunch Anglophile and is thus irritated by the patriotism of Mrs. Khanna.
- Parzan Dastur as Silent Sardarji: A Sikh boy at Camp Sunshine who usually does not speak, but begs Anjali Sharma not to go when she decides to leave the summer camp. He likes Anjali Khanna.
- Neelam Kothari as Neelam (special appearance): She is the host of The Neelam Show, the television programme which Anjali Khanna loves.
- Nikhil Advani in cameo and extra appearance (in Neelam's talk show segment)
- Manish Malhotra in cameo as college student (Sitting on the steps of college when Anjali wears feminine clothing)
- Farah Khan in cameo and extra appearances (in Neelam's talk show and sitting on the steps of college when Anjali wears feminine clothing)
- Geeta Kapoor in the song "Tujhe Yaad Na Meri Aayee"
- Hiroo Johar in cameo as a college professor (walking down the steps of college when Anjali wears feminine clothing)
Answer: Shah Rukh Khan
Student: | Who were Rani's costars in her third movie? | NIv2 | task235_iirc_question_from_subtext_answer_generation | zs_opt |
Q: You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Hebrew.
Alfred Mann configurou a sua fundação para avançar com esta pesquisa porque viu que o capital de risco nunca financiaria algo do género.
A: | אלפרד מאן הקים קרן זו כדי לקדם מחקר זה מאחר והוא ראה שאין הון סיכון שייכנס למשהו כזה. | NIv2 | task1278_ted_translation_pt_he | zs_opt |
Detailed Instructions: In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel.
Problem:OUkufmiXHVAzDiIQ
Solution: | kfmXHVzDQ | NIv2 | task365_synthetic_remove_vowels | zs_opt |
You are given a sentence in Italian. Your job is to translate the Italian sentence into Portugese.
[EX Q]: Tutto questo in una dimensione così minuta.
[EX A]: Isto tudo numa escala muito pequena.
[EX Q]: E poi cercavamo dei timer e delle strutture di dati e cercavamo di relazionarle al mondo reale — a potenziali bersagli.
[EX A]: Depois procurámos temporizadores e estruturas de dados e tentámos relacioná-las com o mundo real — com potenciais alvos do mundo real.
[EX Q]: E 'l'unica minaccia, l'unica influenza che la barriera ha dovuto affrontare.
[EX A]: | É a única ameaça, a única influência com a qual o recife teve de lidar.
| NIv2 | task1255_ted_translation_it_pt | fs_opt |
Detailed Instructions: In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.
Q: Not that I'm against plastic surgery but some expectations for people esp women cannot be achieved with a fucking treadmill and squats
A: | No | NIv2 | task609_sbic_potentially_offense_binary_classification | zs_opt |
In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc.
To keep your pens organized on your desktop | you can use a cup to place them in. | NIv2 | task080_piqa_answer_generation | zs_opt |
You will be given a definition of a task first, then some input of the task.
Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.
1 Which cocktail consisting of tequila and triple sac and lemon or lime juice has a name which means daisy in Spanish?
Output: | margarita | NIv2 | task898_freebase_qa_answer_generation | zs_opt |
In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be characterized by being or having the Tail or not. Being characterized usually describes entities' general characteristics such as rose is red, or subjective attributes such as thirst is uncomfortable. It can also map to descriptors that speak to the substance or value of items such as meat has the property of being stored in the freezer or bike is powered by a person's legs. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Let me give you an example: Head: water<sep>Tail: effect of making things wet
The answer to this example can be: Yes
Here is why: This is a good example. The water can be characterized by making things wet.
OK. solve this:
Head: PersonX answers PersonY's letter<sep>Tail: to invite PersonY
Answer: | No | NIv2 | task1212_atomic_classification_hasproperty | fs_opt |
In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.
One example is below.
Q: Preheat oven to 375 degrees., Boil syrup, sugar and shortening over medium heat, stirring constantly., Remove from heat., Gradually stir in flour and nuts., Drop by teaspoonfuls about 3 inches apart on lightly greased cookie sheet., Bake 5 to 6 min., Remove from oven and let stand 5 min, before removing from sheet., May be rolled into cylindrical shape while still hot., If cooled too much, return to oven for a minute., Yield: 4 dozen cookies.
A: flour, nuts, corn syrup, shortening, brown sugar
Rationale: This is a good example, as we see the NER is generated correctly from the directions.
Q: Simmer cherry juice in a saucepan over medium-high heat, stirring frequently, until the juice is reduced to about 1/2 cup in volume, about 20 to 25 minutes. Remove from heat and pour into a bowl to cool to room temperature., Pour reduced cherry juice, red wine vinegar, and white vinegar together in a blender; add mustard, chile-garlic sauce, salt, and pepper. Blend for 30 seconds. Add a drop of grapeseed oil and blend another 30 seconds. Pour remaining oil into the blender; blend for 2 minutes.
A: | cherry juice, red wine vinegar, white vinegar, mustard, chile-garlic sauce, salt, grapeseed oil | NIv2 | task571_recipe_nlg_ner_generation | fs_opt |
Definition: In this task, you will be shown a Persian passage and question. You need to write a answer for the question. Try to keep your answers as short as possible.
Input: قَزوین یکی از شهرهای ایران است که در قسمت مرکزی این کشور واقع شده و در گذشته برای مدتی پایتخت ایران نیز بوده است. شهر قزوین، مرکز استان قزوین، در بلندای ۱٬۲۷۸ متری از سطح دریا واقع شده است. تاریخچه و ریشه شهر قزوین به دوران ساسانیان باز میگردد زمانی که به دستور شاپور پادشاه ساسانی رونق یافت. قزوین شاهراه اقتصادی جاده ابریشم، سالها محل گذر تجار و بازرگانانی بود که کالاهای خود را از شرق به غرب میبردند. قزوین در زمان حکومت صفوی ۵۷ سال پایتخت ایران بوده و از همین رو دارای اماکن و موزههای تاریخی بسیاری است. قزوین پایتخت بزرگ خوشنویسی ایران است و از جمله خوشنویسان معروف خط پارسی میتوان به میرعماد قزوینی اشاره کرد. قزوین از نظر تعداد اثر تاریخی رتبه نخست در ایران و سوم در جهان را دارد، که از این آثار کهن و باستانی گوناگون میتوان کاروانسرای سعدالسلطنه، مسجد جامع قزوین، میمون قلعه، حمام قجر، آب انبار سردار، پیغمبریه، کاخ چهلستون، امامزاده حسین و خیابان سپه (اولین خیابان ایران) نام برد.
Question: قزوین در کدام قسمت ایران واقع شده است؟
Output: | مرکزی | NIv2 | task395_persianqa_answer_generation | zs_opt |
Instructions: Given a sentence with a missing word, pick the answer option that best fills out the missing word in the sentence. Indicate each answer with its index ('a', 'b', 'c', 'd').
Input: Plants typically take ____ to three years to fully mature.\Question: Choose the right answer from options given a) two b) nine c) eight d) seven
Output: | a | NIv2 | task1360_numer_sense_multiple_choice_qa_generation | zs_opt |
Indicate with `Yes` if the given question involves the provided reasoning `Category`. Indicate with `No`, otherwise. We define five categories of temporal reasoning. First: "event duration" which is defined as the understanding of how long events last. For example, "brushing teeth", usually takes few minutes. Second: "transient v. stationary" events. This category is based on the understanding of whether an event will change over time or not. For example, the sentence "he was born in the U.S." contains a stationary event since it will last forever; however, "he is hungry" contains a transient event since it will remain true for a short period of time. Third: "event ordering" which is the understanding of how events are usually ordered in nature. For example, "earning money" usually comes before "spending money". The fourth one is "absolute timepoint". This category deals with the understanding of when events usually happen. For example, "going to school" usually happens during the day (not at 2 A.M). The last category is "frequency" which refers to how often an event is likely to be repeated. For example, "taking showers" typically occurs ~5 times a week, "going to Saturday market" usually happens every few weeks/months, etc.
--------
Question: Sentence: The Vice President's guidance was we need to take them out."".
Question: How long has he wanted to take them out?
Category: Event Duration.
Answer: No.
Question: Sentence: During a blackout , the house is attacked by aliens , who had previously killed Joe and abducted Iris .
Question: Were the aliens still present in the attacked house the next day?
Category: Transient v. Stationary.
Answer: No.
Question: Sentence: In a matter of 48 hours, Alexander II planned to release his plan for the duma to the Russian people.
Question: What did Alexander II do before releasing his plan?
Category: Event Ordering.
Answer: | Yes.
| NIv2 | task019_mctaco_temporal_reasoning_category | fs_opt |
In this task, you need to answer the given multiple-choice question on the physics. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.
Q: Problem: 36 men can complete a piece of work in 18 days . in how many days will 27 men complete the same work ?
Options: a ) 12 , b ) 18 , c ) 22 , d ) 24 , e ) 26
A: | d | NIv2 | task1422_mathqa_physics | zs_opt |
Given the task definition and input, reply with output. In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is sexually offensive, 2) no, otherwise. Emphasis on sexually offensive or any lewd reference. Generate label 'no' for offensive posts that do not reference sexually explicit content. Warning: the examples and instances may contain offensive language.
RT @itsDorry: school doesnt even test your intelligence it tests ur memory...
....it tests my ability to keep calm and not slap a bitch
| No | NIv2 | task608_sbic_sexual_offense_binary_classification | zs_opt |
TASK DEFINITION: You are given a statement written in Hindi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
PROBLEM: Statement: तरौल के तालुकेदार बाबू गुलाब सिंह ने अंग्रेजी सेना के छक्के छुड़ा दिए थे। अंग्रेजी सेना छितपालगढ़ से तारागढ़ पर चढ़ाई की तो बाबू गुलाब सिंह व उनके भाई बाबू मेदनी सिंह ने हफ्तों तक अंग्रेजों से लोहा लिया। हालाकि उन्हें मालूम था कि अंग्रेजी सेना के सामने लड़ना मौत के मुँह में जाना है, फिर भी भारत के सपूतों ने अंतिम समय तक किले के समीप अंग्रेजी सेना को फटकने नहीं दिया। जब <MASK> से लखनऊ अंग्रेजी सैनिक क्रांतिकारियों के दमन के लिए जा रहे थे।
Option A: इलाहाबाद
Option B: प्रतापगढ़
Option C: गाँव
Option D: बकुलाही
SOLUTION: इलाहाबाद
PROBLEM: Statement: कुछ यूरोपीय हथियार प्रणालियां लोक खेल और आत्मरक्षा के तरीकों के रूप में बचे हुए है। इनमें छड़ी-युद्ध प्रणाली जैसे <MASK> का क्वाटरस्टाफ, आयरलैंड का बाटायरेच्ट, पुर्तगाल का जोगो दो पउ और कानारी आइसलैंड के डुवेगो डेल पालो शैली शामिल है।
Option A: भारत
Option B: इंग्लैंड
Option C: ग्रीस
Option D: गयाना
SOLUTION: इंग्लैंड
PROBLEM: Statement: देश में रावी और ब्यास नदी जल विवाद काफी पुराना है। यह <MASK> के दो राज्यों पंजाब (भारत) और हरियाणा के बीच रावी और ब्यास नदियों के अतरिक्त पानी के बंटवारे को लेकर हैं। मुकदमे सालों से अदालतों में हैं।
Option A: हिमाचल
Option B: हरियाणा
Option C: भारत
Option D: आयरलैंड
SOLUTION: | भारत
| NIv2 | task947_wiki_cloze_hi_multiple_choice_question_answering | fs_opt |
Teacher:You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Polish.
Teacher: Now, understand the problem? Solve this instance: وكإنسانة ، فإنه يبعث فيني الخوف من الله.
Student: | Jako człowieka, napełnia bojaźnią Bożą. | NIv2 | task1107_ted_translation_ar_pl | zs_opt |
Q: In this task, you're given reviews from Amazon's products. Your task is to generate the Summary of the review.
I purchased white certified refurbished Beats 2.0 wired headphones on September 21, 2017 and the item was obviously defected as the battery burnt out in less than 2 months. I sent a note asking to please extend warranty coverage or provide a replacement and I have not received a response. Do not purchase.
A: | Headphone batteries burnt out in less than 2 months! | NIv2 | task618_amazonreview_summary_text_generation | zs_opt |
Detailed Instructions: In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.
Problem:Sentence 1: Willie is on his way home from a concert.
Sentence 3: He pulls over to see what's wrong
Sentence 4: The engine was smoking very badly
Sentence 5: His car engine is blown up!
Option 1: His car is running smoothly.
Option 2: He hears a loud noise coming from his car.
Solution: | Option 2 | NIv2 | task065_timetravel_consistent_sentence_classification | zs_opt |
instruction:
In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb
question:
What is the part-of-speech tag of the word "scientist" in the following question: What is the diameter of the lunar feature named after an Egyptian earth scientist ?
answer:
NN
question:
What is the part-of-speech tag of the word "population" in the following question: What is the population of the county where the racecourse home to the world-famous Grand National steeplechase is located ?
answer:
NN
question:
What is the part-of-speech tag of the word "by" in the following question: When was the boat commanded by the oldest korvettenkapitän launched ?
answer:
| IN
| NIv2 | task382_hybridqa_answer_generation | fs_opt |
Detailed Instructions: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Q: Head: PersonX gives PersonY a number<sep>Tail: communicate information.
A: | Yes | NIv2 | task1201_atomic_classification_xintent | zs_opt |
In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with "Contradiction", "Neutral", or "Entailment".
Premise: But don't dilly-dally for too long. Once it's published we are all going to look a little risible if we have made no adjustments to what is after all known as being predominantly my own design of gallery. Also I am a bit older than the rest of you but you can perhaps understand that I don't want to drop dead without a proper and public recantation. <sep> Hypothesis: he doesn't want to drop dead without a proper and public recantation | Entailment | NIv2 | task1388_cb_entailment | zs_opt |
You will be given a definition of a task first, then some input of the task.
In this task, you are given a hateful post in English from online platforms. You are expected to classify the target being harassed in the post as individual or generic, i.e., single person or a group of people. Note that the URLs in the text have been replaced with [Link].
Post: Everyone calls u btch, and u don't like it? Bitch like whaaat?! Who wouldnt be called bitch u wore like a whore waiting for someone to dig their dick so stfu barbie yo' nigga disagree!
Output: | Individual | NIv2 | task337_hateeval_classification_individual_en | zs_opt |
Definition: You will be given a passage consisting of set of facts and a question as input. The task is to answer a question of form 'Where is <person_name>?' using one of the given facts to determine the latest location of the person. Answer should be a word/phrase describing the location from the supporting fact. Avoid answers that are incomplete or incorrect.
Input: Passage: Mary travelled to the bedroom. Daniel moved to the hallway. Daniel journeyed to the garden. Daniel journeyed to the hallway. Question: Where is Daniel?
Output: | hallway | NIv2 | task083_babi_t1_single_supporting_fact_answer_generation | zs_opt |
Instructions: Write a correct answer for the question. You should reason about prototypical situations and provide the correct answer. Avoid answers that provide incomplete justification for the question.
Input: many hunters wear camouflage in the woods name a pattern youd be surprised to see a hunter wear
Output: | polka dots | NIv2 | task820_protoqa_answer_generation | zs_opt |
Read the given text and if it has abusive content then indicate via "yes". Otherwise indicate via"no".
We consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].
Q: the poster doesn't realize the US has the world's best doctors. One could argue that without universal healthcare, it's a bigger financial burden, but arguing that the level of care is lower because it's not free is ridiculous.
A: | no | NIv2 | task108_contextualabusedetection_classification | zs_opt |
Given the task definition and input, reply with output. In this task, you are given inputs i and A, where i is an integer and A is a list. You need to output the first i elements of A, starting with the 1st element in A. i will always have a value less than the length of A
2, ['3509', 'V', '4061', '5357']
| 3509, V | NIv2 | task063_first_i_elements | zs_opt |
Teacher:In this task, five ordered key facts are given. All the given facts are expressed in natural language. Your job is to generate a story 100 to 1000 words long, that includes all the facts given as input in their order of appearance while expanding upon them to produce a broader, yet coherent, narrative.
Teacher: Now, understand the problem? Solve this instance: Fact1: International smuggler Tony Dumont is plane carrying shipment of industrial diamonds, Fact2: men flee with gems, Fact3: Tony and other passengers including famed author Pamela Vincent are flown to Hong Kong, Fact4: girlfriend go to nightclub run by Mama Lin, Fact5: nightclub run by Mama Lin raised Tony as orphan
Student: | International smuggler Tony Dumont is aboard a plane carrying a shipment of industrial diamonds. It is hijacked by men who flee with the gems. Tony and other passengers, including famed author Pamela Vincent, are flown to Hong Kong, where he doesnt get to say goodbye because Pamela is mobbed by the press. It turns out Tony was mastermind of the heist. He goes to Macao to see girlfriend Jean Blake and old friend Michael Quisto. They go to the nightclub run by Mama Lin, who raised Tony as an orphan. Pamela is among the clubs customers that night, so they renew their acquaintance. Jean is angered by Tony abandoning her at the club. He took off with henchmen Nicco and Boris to get the diamonds, but they are ambushed. Tony is told that Quisto was the snitch who betrayed them. Ordered by boss Bendesh to kill the informer, Tony hesitates, but Quisto stumbles off a gangplank into a boats netting and is dragged to his death. Tony becomes romantically involved with Pamela, so Jean breaks off their relationship. Upset by his friends death, Tony wants to reform and get out of the business. He travels to San Francisco to find Pamela, only to learn she has written a new book with a character based on him, and now wants nothing more to do with him, having taken up with a tennis player. Jean and Mama Lin try to help Tony settle matters with his former accomplices, but accidentally lead him into Niccos trap. The police arrive in time to take Tony and Nicco into custody, leaving the women by themselves, wondering whats to become of Tony. | NIv2 | task103_facts2story_long_text_generation | zs_opt |
In this task, you need to count the number of words in a sentence that start with the given letter. Answer with numbers and not words.
Sentence: 'a fire hydrant beside a burned building in a city'. How many words start with the letter 'a' in the sentence.
3
Sentence: 'people in a field are looking up at a kite'. How many words start with the letter 'u' in the sentence.
1
Sentence: 'a male in a wet suit surfing on a black and white board'. How many words start with the letter 'a' in the sentence.
| 4
| NIv2 | task162_count_words_starting_with_letter | fs_opt |
In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.
Ex Input:
[[42, -31], [-46, -10, 45, -17, -21], [27, 27, 42, 29, 14], [-37, 14, 11], [-38, -17, 3, 40], [-2, -44, 34], [-40, -17], [24, 37, 50, 26], [47, 25, 19], [-41, -46, -29, -11], [35, 45], [-27, -13, 41, -12], [43, 3, -11, -37]]
Ex Output:
[42, 460, 588, 14, -1520, 2992, -40, 31200, 0, -46, 0, -12, 0]
Ex Input:
[[-19, -2, 37], [39, 34, 31, -14, 23], [-3, 40], [3, -6, 37, 15], [-29, 24, -37]]
Ex Output:
[-2, -476, 40, -6, 24]
Ex Input:
[[9, -30, -31, -47], [14, -2], [-23, 45, 11], [9, 25, 39, 31, -14], [-34, 48, -12, -5, -32], [-40, -25, -23, -6, -28], [32, 45, 42, 42], [-32, 6, -17, 44, 39], [11, 29], [44, -31, -39], [-32, 6], [-39, -10]]
Ex Output:
| [-30, -28, 0, -14, -626688, -6720, 56448, -8448, 0, 44, -192, -10]
| NIv2 | task851_synthetic_multiply_evens | fs_opt |
You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.
This is a paraphrasing task. In this task, you're given a sentence and your task is to generate another sentence which express same meaning as the input using different words.
Giraffes like Acacia leaves and hay, and they can consume 75 pounds of food a day.
Solution: A giraffe can eat up to 75 pounds of Acacia leaves and hay daily.
Why? Input and output sentence have same meaning in different words.
New input: yes , but distantly distantly yes , distance you 've transformed your passion into a hobby you shouldnt treat your talent that way !
Solution: | yes , but remotely true yes , you 've turned your passion into a hobby . | NIv2 | task177_para-nmt_paraphrasing | fs_opt |
Q: You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Portugese.
فقدت أسرته كل شيء ، وفي الحادية عشرة من عمره ، كان عليه أن يعيش بين الموتيلات مع أبيه ، تلك الموتيلات التي تقوم بأخذ كل الطعام الذي يملكونه وتحتجزه عندها حتى يتمكنوا من دفع الفاتور.
A: | A sua família perdeu tudo e com 11 anos ele teve de morar em motéis com o seu pai motéis que retinham toda a comida deles até que pudessem pagar a conta. | NIv2 | task1109_ted_translation_ar_pt | zs_opt |
Given the task definition, example input & output, solve the new input case.
You are given a sentence in English. Your job is to translate the English sentence into Portugese.
Example: Astronomers now believe that every star in the galaxy has a planet, and they speculate that up to one fifth of them have an Earth-like planet that might be able to harbor life, but we haven't seen any of them.
Output: Os astrónomos acreditam que cada estrela da galáxia tem um planeta, e especulam que até um quinto deles tem um planeta do tipo da Terra que poderá ter vida, mas ainda não vimos nenhum deles.
The English sentence is correctly translated into Portugese, because the meaning is preserved.
New input case for you: So I want to talk about that as an opportunity that we really have failed to engage with very well in this country and, in fact, worldwide.
Output: | Por isso quero falar de uma oportunidade que realmente temos perdido neste país e, de facto, em todo o mundo. | NIv2 | task1094_ted_translation_en_pt | fs_opt |
Teacher: You are given a sentence in Galician. Your job is to translate the Galician sentence into Arabic.
Teacher: Now, understand the problem? If you are still confused, see the following example:
É basicamente un caldeiro que rota.
Solution: ويوجد أساسا مرجل دوار.
Reason: The Galician sentence is correctly translated into Arabic, because the meaning is preserved.
Now, solve this instance: Agora, o mobiliario familiar ameaza, o chan encóstase e os pomos só ceden se pelexas coas dúas mans.
Student: | الآن ، أثاث مألوف يلوح في الأفق ، إمالة طوابق ، ومقابض أبواب تذعن فقط عند صرعها بكلتا اليدين. | NIv2 | task1241_ted_translation_gl_ar | fs_opt |
Detailed Instructions: The provided files include famous book titles and sentences in the English language, and we ask you to translate those to the Spanish Language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and form of each sentence in the Spanish language. 2) Also names, dates and places should be preserved it should not get translated.
Problem:We must wait, it may be for many years.
Solution: | Debemos esperar, puede ser por muchos años. | NIv2 | task1651_opus_books_en-es__translation | zs_opt |
In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.
Example input: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.
Example output: N
Example explanation: Tom's reason for buying the fruit is not known.
Q: Sentence 1: A collage of stop-action surfing pictures. Sentence 2: they were married
A: | N | NIv2 | task190_snli_classification | fs_opt |
Detailed Instructions: In this task, you are given an input list A. If the count of numbers is more than that of alphabets in the list, answer 'Numbers Win'. If the count of alphabets is more than that of numbers in the list, answer 'Alphabets Win'. If the count of numbers is same as that of alphabets in the list, answer 'Numbers and Alphabets are Tied'.
Q: ['i', '1269', 'U', 't', 'P', '3847', '1507', 't', 'O', 'M', 'Q', '7453', 'j', 'w', 'r', '6557', 'S', '8105', '1353', '2437', 'Z', 'D', 'I', '5345', 'g', '9679', '5015', 'l']
A: | Alphabets Win | NIv2 | task523_find_if_numbers_or_alphabets_are_more_in_list | zs_opt |
Read the given sentence and if it is a general advice then indicate via "yes". Otherwise indicate via "no". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.
Would you like to go over a few techniques i have learned to help cope ? | no | NIv2 | task115_help_advice_classification | zs_opt |
You will be given a definition of a task first, then some input of the task.
In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonY or others will want what is mentioned in the Tail or not. In this task, wanting is a postcondition desire on the part of PersonY and others, respectively. For example, as a result of PersonX giving PersonY gifts, PersonY may want to open the gift. Classify your answers into "Yes" and "No". The phrase may also contain "___", a placeholder that can be an object, a person, and/or an action.
Head: PersonX hides PersonX's ___ in PersonY's hands<sep>Tail: to pull away
Output: | Yes | NIv2 | task1198_atomic_classification_owant | zs_opt |
Definition: You are given a statement written in Telugu. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .
Input: Statement: 1934లో అప్పటి ఆంధ్ర విశ్వవిద్యాలయం ఉపకులపతి డా||సర్వేపల్లి రాధాకృష్ణన్ ఇతడిని విశాఖపట్టణంలోని మిసెస్ ఏ.వి.ఎన్.కళాశాలలో తెలుగుపండితుడిగా నియమించాడు. తరువాత పదోన్నతి పొంది అదే కళాశాలలో ఉపన్యాసకుడిగా పనిచేశాడు.ఆంధ్ర విశ్వవిద్యాలయం బోర్డ్ ఆఫ్ స్టడీస్కు అధ్యక్షుడిగా నియమింపబడ్డాడు. 1951లో <MASK>లోని ఉస్మానియా విశ్వవిద్యాలయంలో ఆంధ్రోపన్యాసకుడిగా చేరాడు. 1957లో రీడర్గా, 1964లో ప్రొఫెసర్గా, తెలుగు శాఖాధ్యక్షుడిగా పదోన్నతి పొందాడు. 1974-1975ల మధ్యకాలంలో ఎమినెంట్ ప్రొఫెసర్గా, 1975 నుండి 1978 వరకు యు.జి.సి.ప్రొఫెసరుగా పదవీ బాధ్యతలు నిర్వహించాడు. ఇతడి పర్యవేక్షణలో 15మంది పి.హెచ్.డి, ఒకరు ఎం.ఫిల్ పట్టాలను పొందారు. ఇతని శిష్యగణంలో ఎం.కులశేఖరరావు, ఇరివెంటి కృష్ణమూర్తి, పి.యశోదారెడ్డి, సి.నారాయణరెడ్డి, ముద్దసాని రామిరెడ్డి మొదలైనవారు ఉన్నారు.
Option A: ఆకుతీగపాడు
Option B: యండగండి
Option C: హైదరాబాదు
Option D: మూల
Output: | హైదరాబాదు | NIv2 | task954_wiki_cloze_te_multiple_choice_question_answering | zs_opt |
Instructions: Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.
Input: THEM: i would like the ball and 2 hats YOU: no, you can have the books and the ball but i want the 4 hats THEM: ok.
Output: | Yes | NIv2 | task1384_deal_or_no_dialog_classification | zs_opt |