xsum_6789_50000_25000_v1_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_6789_50000_25000_v1_train")

topic_model.get_topic_info()

Topic overview

• Number of topics: 255
• Number of training documents: 50000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - mr - police - people - would	5	-1_said_mr_police_people
0	league - goal - win - game - foul	24458	0_league_goal_win_game
1	labour - eu - party - vote - referendum	7343	1_labour_eu_party_vote
2	olympic - athlete - race - sport - gold	1358	2_olympic_athlete_race_sport
3	cricket - wicket - england - test - batsman	1144	3_cricket_wicket_england_test
4	school - education - teacher - pupil - student	781	4_school_education_teacher_pupil
5	rail - transport - rmt - train - bridge	482	5_rail_transport_rmt_train
6	nhs - care - health - patient - hospital	477	6_nhs_care_health_patient
7	boko - haram - president - african - africa	471	7_boko_haram_president_african
8	syrian - syria - assad - rebel - iraq	448	8_syrian_syria_assad_rebel
9	fire - blaze - smoke - firefighter - rescue	345	9_fire_blaze_smoke_firefighter
10	murray - wimbledon - tennis - slam - seed	290	10_murray_wimbledon_tennis_slam
11	film - actor - star - movie - award	266	11_film_actor_star_movie
12	dup - sinn - fin - ireland - northern	258	12_dup_sinn_fin_ireland
13	fight - boxing - champion - title - fury	257	13_fight_boxing_champion_title
14	crash - road - collision - driver - car	247	14_crash_road_collision_driver
15	mercedes - hamilton - f1 - race - rosberg	238	15_mercedes_hamilton_f1_race
16	coastguard - lifeboat - rescue - boat - rnli	235	16_coastguard_lifeboat_rescue_boat
17	china - chinese - hong - kong - chinas	230	17_china_chinese_hong_kong
18	ukraine - russian - russia - ukrainian - putin	221	18_ukraine_russian_russia_ukrainian
19	taliban - pakistan - afghan - pakistani - afghanistan	218	19_taliban_pakistan_afghan_pakistani
20	mcilroy - golf - birdie - open - par	218	20_mcilroy_golf_birdie_open
21	dog - animal - dogs - cat - rspca	208	21_dog_animal_dogs_cat
22	data - security - nsa - computer - malware	207	22_data_security_nsa_computer
23	cancer - patient - treatment - disease - cell	198	23_cancer_patient_treatment_disease
24	maduro - venezuela - mexico - morales - president	198	24_maduro_venezuela_mexico_morales
25	energy - climate - gas - wind - carbon	197	25_energy_climate_gas_wind
26	sexual - indecent - court - assault - victim	182	26_sexual_indecent_court_assault
27	sale - store - retail - tesco - retailer	174	27_sale_store_retail_tesco
28	marriage - church - bishop - samesex - cardinal	172	28_marriage_church_bishop_samesex
29	album - song - music - band - chart	170	29_album_song_music_band
30	apple - samsung - phone - technology - mobile	163	30_apple_samsung_phone_technology
31	trump - republican - clinton - republicans - mr	156	31_trump_republican_clinton_republicans
32	yn - ar - wedi - ei - mae	148	32_yn_ar_wedi_ei
33	ebola - virus - vaccine - outbreak - zika	148	33_ebola_virus_vaccine_outbreak
34	planet - particle - earth - space - universe	143	34_planet_particle_earth_space
35	flood - flooding - water - weather - rain	139	35_flood_flooding_water_weather
36	migrant - refugee - asylum - hungary - migrants	138	36_migrant_refugee_asylum_hungary
37	korea - north - korean - kim - missile	130	37_korea_north_korean_kim
38	paris - french - attack - france - police	122	38_paris_french_attack_france
39	memorial - war - battle - soldier - regiment	120	39_memorial_war_battle_soldier
40	plane - flight - aircraft - pilot - airport	112	40_plane_flight_aircraft_pilot
41	man - det - incident - wearing - police	111	41_man_det_incident_wearing
42	art - painting - artist - exhibition - gallery	109	42_art_painting_artist_exhibition
43	growth - rate - economy - inflation - bank	106	43_growth_rate_economy_inflation
44	prison - prisoner - prisons - offender - prisoners	104	44_prison_prisoner_prisons_offender
45	bank - banking - barclays - hsbc - rbs	103	45_bank_banking_barclays_hsbc
46	earthquake - quake - nepal - magnitude - hurricane	101	46_earthquake_quake_nepal_magnitude
47	shooting - police - officer - black - gun	100	47_shooting_police_officer_black
48	greece - greek - eurozone - bailout - greeces	99	48_greece_greek_eurozone_bailout
49	housing - price - property - house - home	94	49_housing_price_property_house
50	morsi - egypt - brotherhood - egyptian - cairo	93	50_morsi_egypt_brotherhood_egyptian
51	airport - heathrow - runway - flight - gatwick	92	51_airport_heathrow_runway_flight
52	murder - arrested - suspicion - custody - postmortem	92	52_murder_arrested_suspicion_custody
53	zoo - tiger - animal - elephant - rhino	90	53_zoo_tiger_animal_elephant
54	festival - event - music - edinburgh - organiser	90	54_festival_event_music_edinburgh
55	book - novel - author - prize - writer	89	55_book_novel_author_prize
56	snooker - osullivan - frame - world - gerwen	88	56_snooker_osullivan_frame_world
57	unsupported - updated - playback - device - media	87	57_unsupported_updated_playback_device
58	india - indias - delhi - indian - woman	86	58_india_indias_delhi_indian
59	trust - death - care - hospital - baby	86	59_trust_death_care_hospital
60	bbc - licence - s4c - fee - wales	84	60_bbc_licence_s4c_fee
61	prince - queen - royal - duchess - duke	78	61_prince_queen_royal_duchess
62	index - benchmark - nikkei - chinas - growth	78	62_index_benchmark_nikkei_chinas
63	abuse - police - child - sexual - exploitation	77	63_abuse_police_child_sexual
64	belfast - ira - finucane - murder - family	76	64_belfast_ira_finucane_murder
65	council - site - development - building - regeneration	74	65_council_site_development_building
66	obesity - sugar - food - obese - drink	73	66_obesity_sugar_food_obese
67	murder - court - heard - knife - trial	72	67_murder_court_heard_knife
68	steel - tata - talbot - plant - port	71	68_steel_tata_talbot_plant
69	bird - wildlife - birds - rspb - conservation	67	69_bird_wildlife_birds_rspb
70	drug - cannabis - heroin - drugs - marijuana	64	70_drug_cannabis_heroin_drugs
71	pen - macron - fillon - le - french	61	71_pen_macron_fillon_le
72	sp - nasdaq - dow - rose - index	61	72_sp_nasdaq_dow_rose
73	israel - israeli - palestinian - palestinians - hamas	59	73_israel_israeli_palestinian_palestinians
74	ftse - shares - share - pound - index	59	74_ftse_shares_share_pound
75	updated - gmt - 2017 - bst - last	57	75_updated_gmt_2017_bst
76	broadband - bt - ofcom - openreach - customer	57	76_broadband_bt_ofcom_openreach
77	vw - emission - car - volkswagen - diesel	57	77_vw_emission_car_volkswagen
78	iran - nuclear - irans - iranian - rouhani	56	78_iran_nuclear_irans_iranian
79	cushnahan - nama - ireland - northern - ni	55	79_cushnahan_nama_ireland_northern
80	alcohol - drinking - drink - wine - minimum	53	80_alcohol_drinking_drink_wine
81	fraud - money - court - judge - account	53	81_fraud_money_court_judge
82	pope - vatican - francis - church - catholic	53	82_pope_vatican_francis_church
83	pollution - air - emission - nitrogen - no2	52	83_pollution_air_emission_nitrogen
84	pokemon - game - console - nintendo - vr	52	84_pokemon_game_console_nintendo
85	driver - road - camera - driving - speed	52	85_driver_road_camera_driving
86	waste - recycling - bag - plastic - food	52	86_waste_recycling_bag_plastic
87	farc - peace - eln - rebel - colombian	50	87_farc_peace_eln_rebel
88	berlusconi - pp - rajoy - spains - catalan	50	88_berlusconi_pp_rajoy_spains
89	thailand - thai - king - yingluck - thailands	49	89_thailand_thai_king_yingluck
90	quantum - computer - machine - computing - ai	46	90_quantum_computer_machine_computing
91	kosovo - bosnian - serbia - serb - srebrenica	45	91_kosovo_bosnian_serbia_serb
92	drug - cannabis - cocaine - drugs - court	45	92_drug_cannabis_cocaine_drugs
93	rousseff - petrobras - temer - brazils - corruption	45	93_rousseff_petrobras_temer_brazils
94	yemen - houthis - hadi - houthi - saudi	44	94_yemen_houthis_hadi_houthi
95	tax - budget - chancellor - cut - spending	44	95_tax_budget_chancellor_cut
96	train - tram - driver - raib - rail	44	96_train_tram_driver_raib
97	fbi - comey - trump - clinton - email	44	97_fbi_comey_trump_clinton
98	drone - aircraft - drones - aviation - unmanned	43	98_drone_aircraft_drones_aviation
99	smoking - tobacco - cigarette - ecigarettes - smoker	42	99_smoking_tobacco_cigarette_ecigarettes
100	hillsborough - disaster - liverpool - 1989 - crush	41	100_hillsborough_disaster_liverpool_1989
101	council - local - cut - budget - tax	40	101_council_local_cut_budget
102	google - facebook - user - video - search	40	102_google_facebook_user_video
103	syria - islamic - family - son - iraq	39	103_syria_islamic_family_son
104	missing - search - body - police - seen	38	104_missing_search_body_police
105	airline - airbus - airlines - aer - boeing	38	105_airline_airbus_airlines_aer
106	car - psa - vehicle - gm - battery	36	106_car_psa_vehicle_gm
107	fish - salmon - fishing - water - fishery	36	107_fish_salmon_fishing_water
108	oil - gas - decommissioning - field - sea	36	108_oil_gas_decommissioning_field
109	policing - police - constable - officer - spa	35	109_policing_police_constable_officer
110	fire - cladding - grenfell - tower - block	34	110_fire_cladding_grenfell_tower
111	nuclear - reactor - fukushima - plant - radiation	33	111_nuclear_reactor_fukushima_plant
112	tree - woodland - trees - oak - forest	32	112_tree_woodland_trees_oak
113	milk - dairy - farmer - farmers - farming	32	113_milk_dairy_farmer_farmers
114	abortion - woman - termination - ireland - northern	32	114_abortion_woman_termination_ireland
115	whale - dolphin - whales - sperm - orca	32	115_whale_dolphin_whales_sperm
116	nauru - australia - asylum - australian - seeker	31	116_nauru_australia_asylum_australian
117	driving - clarke - car - causing - crash	31	117_driving_clarke_car_causing
118	stolen - police - bike - haldane - robbery	31	118_stolen_police_bike_haldane
119	meat - horsemeat - milk - food - product	31	119_meat_horsemeat_milk_food
120	wage - living - pay - minimum - worker	30	120_wage_living_pay_minimum
121	belfast - flag - parade - parades - loyalist	30	121_belfast_flag_parade_parades
122	terrorism - arrested - arrest - suspicion - police	29	122_terrorism_arrested_arrest_suspicion
123	manchester - protest - ford - police - london	29	123_manchester_protest_ford_police
124	uber - driver - taxi - ubers - kalanick	28	124_uber_driver_taxi_ubers
125	calais - camp - migrant - jungle - asylum	28	125_calais_camp_migrant_jungle
126	music - streaming - spotify - album - artist	28	126_music_streaming_spotify_album
127	childrens - ofsted - child - council - improvement	28	127_childrens_ofsted_child_council
128	erdogan - turkish - turkey - coup - istanbul	28	128_erdogan_turkish_turkey_coup
129	cuba - cuban - castro - cubans - havana	28	129_cuba_cuban_castro_cubans
130	libya - gaddafi - libyan - tripoli - gaddafis	27	130_libya_gaddafi_libyan_tripoli
131	oil - barrel - opec - price - saudi	26	131_oil_barrel_opec_price
132	trident - nuclear - submarine - renewal - defence	26	132_trident_nuclear_submarine_renewal
133	pistorius - steenkamp - reeva - toilet - intruder	26	133_pistorius_steenkamp_reeva_toilet
134	transgender - gay - marriage - law - samesex	26	134_transgender_gay_marriage_law
135	space - astronaut - peake - tim - iss	25	135_space_astronaut_peake_tim
136	pte - inquest - lcpl - cpl - soldier	25	136_pte_inquest_lcpl_cpl
137	cox - jo - mp - batley - mrs	24	137_cox_jo_mp_batley
138	jackpot - lottery - ticket - camelot - prize	24	138_jackpot_lottery_ticket_camelot
139	pottery - roman - excavation - stone - site	24	139_pottery_roman_excavation_stone
140	wikipedia - woman - women - makeup - female	24	140_wikipedia_woman_women_makeup
141	energy - price - supplier - customer - gas	23	141_energy_price_supplier_customer
142	dinosaur - specimen - fossil - neanderthals - museum	23	142_dinosaur_specimen_fossil_neanderthals
143	yamaha - rossi - marquez - lorenzo - ducati	23	143_yamaha_rossi_marquez_lorenzo
144	execution - death - drug - lethal - executions	22	144_execution_death_drug_lethal
145	tesla - car - selfdriving - vehicle - autonomous	22	145_tesla_car_selfdriving_vehicle
146	famine - drought - somalia - food - aid	22	146_famine_drought_somalia_food
147	inquiry - abuse - survivor - goddard - inquirys	21	147_inquiry_abuse_survivor_goddard
148	mh370 - plane - search - flight - ocean	21	148_mh370_plane_search_flight
149	coin - museum - hoard - treasure - ring	21	149_coin_museum_hoard_treasure
150	assange - wikileaks - extradition - embassy - assanges	21	150_assange_wikileaks_extradition_embassy
151	ride - alton - smiler - towers - merlin	20	151_ride_alton_smiler_towers
152	fm - radio - tv - freedom - medium	19	152_fm_radio_tv_freedom
153	pension - annuity - retirement - income - pensions	19	153_pension_annuity_retirement_income
154	homelessness - homeless - housing - rough - council	19	154_homelessness_homeless_housing_rough
155	facebook - news - fake - medium - social	19	155_facebook_news_fake_medium
156	trade - tpp - nafta - us - mexico	19	156_trade_tpp_nafta_us
157	whisky - distillery - beer - scotch - bottle	19	157_whisky_distillery_beer_scotch
158	court - trigg - heard - ms - eli	19	158_court_trigg_heard_ms
159	nba - curry - lebron - warriors - cleveland	19	159_nba_curry_lebron_warriors
160	ferry - calmac - serco - ferries - contract	18	160_ferry_calmac_serco_ferries
161	hms - ship - navy - shipbuilding - warship	18	161_hms_ship_navy_shipbuilding
162	syria - strike - iraq - mps - military	18	162_syria_strike_iraq_mps
163	childcare - child - parent - inheritance - meal	18	163_childcare_child_parent_inheritance
164	junior - doctor - bma - contract - doctors	18	164_junior_doctor_bma_contract
165	1916 - rising - irish - easter - ireland	18	165_1916_rising_irish_easter
166	condor - guernsey - ship - poole - port	17	166_condor_guernsey_ship_poole
167	hussain - terrorism - terrorist - heard - court	17	167_hussain_terrorism_terrorist_heard
168	unemployment - ons - rate - employment - growth	17	168_unemployment_ons_rate_employment
169	suu - kyi - nld - aung - thein	16	169_suu_kyi_nld_aung
170	eurotunnel - calais - french - eurostar - train	16	170_eurotunnel_calais_french_eurostar
171	bike - cycling - cycle - cyclist - parking	15	171_bike_cycling_cycle_cyclist
172	breath - driving - drinkdriving - limit - driver	15	172_breath_driving_drinkdriving_limit
173	everest - avalanche - mountain - sherpa - icefall	15	173_everest_avalanche_mountain_sherpa
174	reef - coral - vent - seabed - marine	15	174_reef_coral_vent_seabed
175	army - defence - mod - reserve - recruitment	15	175_army_defence_mod_reserve
176	explosion - tianjin - bomb - blast - bethnal	15	176_explosion_tianjin_bomb_blast
177	mayor - devolution - combined - greater - region	15	177_mayor_devolution_combined_greater
178	tax - company - uk - cayman - profit	15	178_tax_company_uk_cayman
179	muslims - ban - muslim - us - order	15	179_muslims_ban_muslim_us
180	growth - output - sector - scotlands - scottish	15	180_growth_output_sector_scotlands
181	suicide - acne - judith - life - mental	14	181_suicide_acne_judith_life
182	bp - spill - oil - rig - deepwater	14	182_bp_spill_oil_rig
183	xinjiang - uighur - uighurs - urumqi - chinese	14	183_xinjiang_uighur_uighurs_urumqi
184	refugee - syrians - syria - syrian - refugees	14	184_refugee_syrians_syria_syrian
185	rea - sykes - davies - fish - race	14	185_rea_sykes_davies_fish
186	mortgage - lending - debt - insolvency - lender	13	186_mortgage_lending_debt_insolvency
187	barnes - pilot - helicopter - crash - fog	13	187_barnes_pilot_helicopter_crash
188	rhodes - statue - igbo - college - oriel	13	188_rhodes_statue_igbo_college
189	edf - hinkley - nuclear - plant - reactor	13	189_edf_hinkley_nuclear_plant
190	sweeney - church - leonard - alder - megans	13	190_sweeney_church_leonard_alder
191	duterte - philippines - mindanao - dutertes - martial	13	191_duterte_philippines_mindanao_dutertes
192	ferry - ship - yoo - sank - sewol	13	192_ferry_ship_yoo_sank
193	norovirus - diarrhoea - hospital - virus - patient	13	193_norovirus_diarrhoea_hospital_virus
194	art - arts - culture - theatre - funding	13	194_art_arts_culture_theatre
195	pipeline - dakota - oil - sioux - project	13	195_pipeline_dakota_oil_sioux
196	climate - temperature - warming - global - ocean	13	196_climate_temperature_warming_global
197	leg - solar - piccard - impulse - borschberg	12	197_leg_solar_piccard_impulse
198	gun - zimmerman - roof - fbi - shooting	12	198_gun_zimmerman_roof_fbi
199	copyright - infringement - megaupload - pirated - piracy	12	199_copyright_infringement_megaupload_pirated
200	bee - hive - beekeeper - honey - tunibee	12	200_bee_hive_beekeeper_honey
201	bombardier - cseries - belfast - bombardiers - learjet	11	201_bombardier_cseries_belfast_bombardiers
202	trudeau - canada - canadian - harper - prentice	11	202_trudeau_canada_canadian_harper
203	object - reopened - evacuated - bomb - street	11	203_object_reopened_evacuated_bomb
204	autism - mental - child - health - autistic	11	204_autism_mental_child_health
205	regiment - lcpl - helmand - afghanistan - soldier	11	205_regiment_lcpl_helmand_afghanistan
206	tunisia - attack - sousse - hotel - essid	11	206_tunisia_attack_sousse_hotel
207	press - leveson - foi - ipso - newspaper	11	207_press_leveson_foi_ipso
208	raf - aircraft - base - mildenhall - squadron	11	208_raf_aircraft_base_mildenhall
209	language - welsh - literature - huws - meri	11	209_language_welsh_literature_huws
210	concert - manchester - grande - ariana - arena	11	210_concert_manchester_grande_ariana
211	lubitz - cockpit - lufthansa - copilot - germanwings	11	211_lubitz_cockpit_lufthansa_copilot
212	facebook - tweet - gamergate - content - user	10	212_facebook_tweet_gamergate_content
213	mine - miner - underground - fyfield - mining	10	213_mine_miner_underground_fyfield
214	ira - sinn - fin - cahill - ireland	10	214_ira_sinn_fin_cahill
215	gear - clarkson - hammond - show - clarksons	10	215_gear_clarkson_hammond_show
216	tree - trees - felling - sheffield - diseased	10	216_tree_trees_felling_sheffield
217	forbes - richest - billionaire - list - billionaires	9	217_forbes_richest_billionaire_list
218	pier - structure - bewl - birnbeck - restore	9	218_pier_structure_bewl_birnbeck
219	bbcscotlandpics - scotlandpicturesbbccouk - picture - selection - instagram	9	219_bbcscotlandpics_scotlandpicturesbbccouk_picture_selection
220	chemical - tianjin - blast - cyanide - sodium	9	220_chemical_tianjin_blast_cyanide
221	lever - ranganathan - gray - spinal - mire	9	221_lever_ranganathan_gray_spinal
222	internet - icann - cac - user - china	9	222_internet_icann_cac_user
223	chandelier - museum - bute - museums - abmu	8	223_chandelier_museum_bute_museums
224	poultry - bird - flu - outbreak - avian	8	224_poultry_bird_flu_outbreak
225	school - parent - thot - dress - circus	8	225_school_parent_thot_dress
226	gambling - casino - machine - betting - machines	8	226_gambling_casino_machine_betting
227	ticket - venue - theatre - ticketing - tickets	8	227_ticket_venue_theatre_ticketing
228	cardiff - solstice - arriva - train - station	8	228_cardiff_solstice_arriva_train
229	hacking - brooks - editor - sun - news	7	229_hacking_brooks_editor_sun
230	sats - gnome - 11 - santa - cam	7	230_sats_gnome_11_santa
231	robot - biomimicry - benyus - robots - robotics	7	231_robot_biomimicry_benyus_robots
232	parkrun - parking - park - laugharne - charge	7	232_parkrun_parking_park_laugharne
233	organ - transplant - donor - donation - optout	7	233_organ_transplant_donor_donation
234	cav - bowers - ramadhan - aerospace - grills	7	234_cav_bowers_ramadhan_aerospace
235	call - scotland - bilston - police - hmics	6	235_call_scotland_bilston_police
236	sao - water - munduruku - tapajos - paulo	6	236_sao_water_munduruku_tapajos
237	eurovision - song - contest - redzepova - entry	6	237_eurovision_song_contest_redzepova
238	livingstone - antisemitism - labour - mann - comment	6	238_livingstone_antisemitism_labour_mann
239	book - publishing - ebook - asi - digital	6	239_book_publishing_ebook_asi
240	befriending - elaine - frsb - older - fundraising	6	240_befriending_elaine_frsb_older
241	strathaven - tipper - scene - police - humbie	6	241_strathaven_tipper_scene_police
242	bay - cardiff - swansea - region - investment	5	242_bay_cardiff_swansea_region
243	cheese - food - outbreak - coli - flicks	5	243_cheese_food_outbreak_coli
244	witheridge - miller - thai - koh - tao	5	244_witheridge_miller_thai_koh
245	yorkshire - tour - depart - cycling - verity	5	245_yorkshire_tour_depart_cycling
246	airline - lufthansa - franceklm - air - flight	5	246_airline_lufthansa_franceklm_air
247	caffel - honourbased - forensic - warning - gill	5	247_caffel_honourbased_forensic_warning
248	torreele - quebec - bissonnette - polish - boissoneault	5	248_torreele_quebec_bissonnette_polish
249	lash - advert - ad - skin - asa	5	249_lash_advert_ad_skin
250	fgm - girl - practice - subjected - woman	5	250_fgm_girl_practice_subjected
251	parkland - wepre - heritage - margam - arnold	5	251_parkland_wepre_heritage_margam
252	coal - aberfan - colliery - gedling - thoresby	5	252_coal_aberfan_colliery_gedling
253	exoffenders - pupil - gwynne - yemms - school	5	253_exoffenders_pupil_gwynne_yemms

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: 1.23.5
• 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: 5.15.0
• Python: 3.10.12