xsum_22457_3000_1500_train

This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.

Usage

To use this model, please install BERTopic:

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("KingKazma/xsum_22457_3000_1500_train")

topic_model.get_topic_info()

Topic overview

• Number of topics: 45
• Number of training documents: 3000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - mr - would - people - also	6	-1_said_mr_would_people
0	win - kick - game - foul - united	1243	0_win_kick_game_foul
1	health - patient - nhs - hospital - cancer	453	1_health_patient_nhs_hospital
2	film - actor - music - song - star	119	2_film_actor_music_song
3	bank - business - share - market - sale	83	3_bank_business_share_market
4	police - northern - ireland - said - crime	80	4_police_northern_ireland_said
5	wicket - england - cricket - test - bowler	67	5_wicket_england_cricket_test
6	president - mr - election - government - farc	67	6_president_mr_election_government
7	labour - party - mr - election - corbyn	62	7_labour_party_mr_election
8	bird - specie - animal - zoo - dna	58	8_bird_specie_animal_zoo
9	school - education - student - teacher - schools	48	9_school_education_student_teacher
10	murder - court - mr - police - said	42	10_murder_court_mr_police
11	crash - police - road - died - collision	42	11_crash_police_road_died
12	rail - transport - said - passenger - train	38	12_rail_transport_said_passenger
13	facebook - console - broadband - game - company	38	13_facebook_console_broadband_game
14	lifeboat - rnli - water - sea - hms	37	14_lifeboat_rnli_water_sea
15	fire - blaze - said - cladding - building	35	15_fire_blaze_said_cladding
16	russia - syria - russian - syrian - military	34	16_russia_syria_russian_syrian
17	girl - child - abuse - court - sexual	32	17_girl_child_abuse_court
18	trump - mr - president - trumps - clinton	29	18_trump_mr_president_trumps
19	man - police - arrested - suspicion - hospital	27	19_man_police_arrested_suspicion
20	murray - tennis - djokovic - wimbledon - grand	26	20_murray_tennis_djokovic_wimbledon
21	medal - gold - olympic - games - world	25	21_medal_gold_olympic_games
22	india - indian - crop - modi - hindu	24	22_india_indian_crop_modi
23	birdie - open - round - golf - mcilroy	23	23_birdie_open_round_golf
24	earth - particle - space - moon - dark	20	24_earth_particle_space_moon
25	madrid - barcelona - foul - assisted - corner	20	25_madrid_barcelona_foul_assisted
26	eu - uk - brexit - european - would	20	26_eu_uk_brexit_european
27	athlete - doping - ioc - olympic - medal	19	27_athlete_doping_ioc_olympic
28	wales - welsh - government - waste - money	18	28_wales_welsh_government_waste
29	race - rosberg - hamilton - mercedes - engine	16	29_race_rosberg_hamilton_mercedes
30	plane - flight - mh370 - aircraft - airlines	16	30_plane_flight_mh370_aircraft
31	fight - pacquiao - mayweather - champion - whyte	14	31_fight_pacquiao_mayweather_champion
32	attack - us - security - bin - killed	14	32_attack_us_security_bin
33	virus - ebola - outbreak - disease - infected	12	33_virus_ebola_outbreak_disease
34	greece - migrant - eu - greek - crisis	12	34_greece_migrant_eu_greek
35	hie - farm - enterprise - energy - funicular	12	35_hie_farm_enterprise_energy
36	inflation - growth - rate - economist - manufacturing	11	36_inflation_growth_rate_economist
37	yn - ar - bod - ei - wedi	11	37_yn_ar_bod_ei
38	cup - group - sredojevic - al - mazembe	11	38_cup_group_sredojevic_al
39	picasso - picture - image - collection - cameron	9	39_picasso_picture_image_collection
40	froome - sky - tour - wiggins - team	8	40_froome_sky_tour_wiggins
41	carnival - event - pride - lgbt - notting	7	41_carnival_event_pride_lgbt
42	cocaine - corkindale - supply - connelly - drug	6	42_cocaine_corkindale_supply_connelly
43	meal - child - school - family - scheme	6	43_meal_child_school_family

Training hyperparameters

• calculate_probabilities: True
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: None
• seed_topic_list: None
• top_n_words: 10
• verbose: False

Framework versions

• Numpy: 1.22.4
• HDBSCAN: 0.8.33
• UMAP: 0.5.3
• Pandas: 1.5.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.2.2
• Transformers: 4.31.0
• Numba: 0.57.1
• Plotly: 5.13.1
• Python: 3.10.12