xsum_108_50000_25000_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_108_50000_25000_train")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 312
  • Number of training documents: 50000
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 said - mr - people - one - would 5 -1_said_mr_people_one
0 film - music - show - song - album 28639 0_film_music_show_song
1 olympic - gold - medal - sport - athlete 1259 1_olympic_gold_medal_sport
2 labour - eu - party - referendum - vote 1178 2_labour_eu_party_referendum
3 foul - box - kick - footed - corner 1082 3_foul_box_kick_footed
4 cricket - wicket - england - test - t20 894 4_cricket_wicket_england_test
5 rugby - wales - scarlets - blues - ospreys 779 5_rugby_wales_scarlets_blues
6 school - education - teacher - pupil - student 495 6_school_education_teacher_pupil
7 boko - haram - african - alshabab - president 454 7_boko_haram_african_alshabab
8 rail - transport - train - bridge - rmt 452 8_rail_transport_train_bridge
9 nhs - patient - health - care - hospital 447 9_nhs_patient_health_care
10 club - football - stadium - league - premier 395 10_club_football_stadium_league
11 murray - wimbledon - tennis - seed - djokovic 310 11_murray_wimbledon_tennis_seed
12 appearance - dedicated - transfer - page - season 290 12_appearance_dedicated_transfer_page
13 fire - blaze - smoke - firefighter - rescue 289 13_fire_blaze_smoke_firefighter
14 energy - climate - gas - electricity - oil 276 14_energy_climate_gas_electricity
15 mercedes - hamilton - race - f1 - lap 271 15_mercedes_hamilton_race_f1
16 space - earth - planet - mission - moon 249 16_space_earth_planet_mission
17 trump - clinton - republican - trumps - mr 240 17_trump_clinton_republican_trumps
18 sexual - victim - indecent - court - sex 239 18_sexual_victim_indecent_court
19 syrian - syria - rebel - aleppo - assad 225 19_syrian_syria_rebel_aleppo
20 coastguard - lifeboat - rescue - water - rnli 206 20_coastguard_lifeboat_rescue_water
21 fight - boxing - champion - mayweather - boxer 202 21_fight_boxing_champion_mayweather
22 road - crash - driver - collision - car 197 22_road_crash_driver_collision
23 flood - flooding - weather - warning - rain 194 23_flood_flooding_weather_warning
24 sinn - dup - fin - party - ireland 179 24_sinn_dup_fin_party
25 taliban - pakistan - afghan - afghanistan - pakistani 178 25_taliban_pakistan_afghan_afghanistan
26 madrid - real - kick - barcelona - assisted 177 26_madrid_real_kick_barcelona
27 tottenham - chelsea - manchester - arsenal - league 176 27_tottenham_chelsea_manchester_arsenal
28 mcilroy - golf - birdie - round - par 174 28_mcilroy_golf_birdie_round
29 china - chinese - hong - kong - beijing 172 29_china_chinese_hong_kong
30 dog - animal - cat - dogs - pet 170 30_dog_animal_cat_dogs
31 arrested - murder - postmortem - police - suspicion 168 31_arrested_murder_postmortem_police
32 yn - ar - wedi - ei - bod 150 32_yn_ar_wedi_ei
33 saudi - qatar - arabia - libya - egypt 149 33_saudi_qatar_arabia_libya
34 african - cup - africa - caf - nations 147 34_african_cup_africa_caf
35 data - security - user - information - tor 147 35_data_security_user_information
36 council - site - development - planning - building 146 36_council_site_development_planning
37 shooting - police - officer - gun - black 139 37_shooting_police_officer_gun
38 court - murder - heard - crown - trial 129 38_court_murder_heard_crown
39 korea - north - korean - kim - nuclear 124 39_korea_north_korean_kim
40 earthquake - quake - nepal - kathmandu - landslide 124 40_earthquake_quake_nepal_kathmandu
41 index - china - chinas - benchmark - market 116 41_index_china_chinas_benchmark
42 painting - artist - art - museum - auction 116 42_painting_artist_art_museum
43 sale - store - tesco - retail - sainsburys 112 43_sale_store_tesco_retail
44 india - indian - modi - bjp - gandhi 111 44_india_indian_modi_bjp
45 airport - heathrow - runway - airports - gatwick 110 45_airport_heathrow_runway_airports
46 abuse - ipcc - police - inquiry - allegation 101 46_abuse_ipcc_police_inquiry
47 israel - israeli - palestinian - palestinians - gaza 98 47_israel_israeli_palestinian_palestinians
48 derry - donegal - tyrone - 01 - antrim 98 48_derry_donegal_tyrone_01
49 bird - rspb - birds - wildlife - eagle 95 49_bird_rspb_birds_wildlife
50 belfast - ira - ireland - mcguinness - irish 95 50_belfast_ira_ireland_mcguinness
51 apple - samsung - phone - smartphone - android 95 51_apple_samsung_phone_smartphone
52 steel - tata - plant - talbot - job 93 52_steel_tata_plant_talbot
53 ukraine - russian - russia - ukrainian - putin 92 53_ukraine_russian_russia_ukrainian
54 war - battle - battalion - soldier - regiment 91 54_war_battle_battalion_soldier
55 cancer - treatment - breast - drug - patient 91 55_cancer_treatment_breast_drug
56 replacements - wigan - try - hull - warrington 90 56_replacements_wigan_try_hull
57 man - det - police - incident - attack 89 57_man_det_police_incident
58 snooker - frame - ding - osullivan - selby 89 58_snooker_frame_ding_osullivan
59 migrant - asylum - refugee - greece - turkey 89 59_migrant_asylum_refugee_greece
60 unsupported - updated - playback - device - media 86 60_unsupported_updated_playback_device
61 council - budget - cut - local - housing 85 61_council_budget_cut_local
62 price - mortgage - property - housing - house 82 62_price_mortgage_property_housing
63 prince - duke - duchess - royal - queen 81 63_prince_duke_duchess_royal
64 crime - police - policing - officer - force 80 64_crime_police_policing_officer
65 paris - french - brussels - attack - attacks 80 65_paris_french_brussels_attack
66 uber - driver - taxi - car - vehicle 77 66_uber_driver_taxi_car
67 greece - greek - eurozone - bailout - greeces 75 67_greece_greek_eurozone_bailout
68 mexico - drug - guzman - cartel - mexican 74 68_mexico_drug_guzman_cartel
69 broadband - bt - openreach - ofcom - customer 72 69_broadband_bt_openreach_ofcom
70 pope - vatican - cardinal - church - francis 67 70_pope_vatican_cardinal_church
71 ftse - share - index - pound - fell 67 71_ftse_share_index_pound
72 updated - bst - gmt - 2017 - 2016 65 72_updated_bst_gmt_2017
73 archaeologist - excavation - archaeological - site - discovery 65 73_archaeologist_excavation_archaeological_site
74 zoo - animal - cub - hunting - lion 63 74_zoo_animal_cub_hunting
75 drug - cocaine - cannabis - drugs - supply 63 75_drug_cocaine_cannabis_drugs
76 bank - banking - account - customer - barclays 62 76_bank_banking_account_customer
77 pen - macron - fillon - french - le 61 77_pen_macron_fillon_french
78 prison - prisoner - prisons - hmp - inmate 59 78_prison_prisoner_prisons_hmp
79 bomb - disposal - evacuated - police - device 59 79_bomb_disposal_evacuated_police
80 child - childrens - care - young - parent 57 80_child_childrens_care_young
81 bishop - church - cardinal - archbishop - diocese 57 81_bishop_church_cardinal_archbishop
82 missing - police - family - search - disappearance 56 82_missing_police_family_search
83 dow - nasdaq - sp - fell - rose 54 83_dow_nasdaq_sp_fell
84 migrant - boat - libya - mediterranean - italian 54 84_migrant_boat_libya_mediterranean
85 iran - nuclear - irans - iranian - iaea 54 85_iran_nuclear_irans_iranian
86 maduro - venezuela - opposition - venezuelan - venezuelas 52 86_maduro_venezuela_opposition_venezuelan
87 gay - transgender - marriage - abortion - law 52 87_gay_transgender_marriage_abortion
88 waste - recycling - bag - landfill - recycled 52 88_waste_recycling_bag_landfill
89 pollution - air - no2 - nitrogen - diesel 51 89_pollution_air_no2_nitrogen
90 fish - fishing - reef - marine - sea 49 90_fish_fishing_reef_marine
91 whale - porpoise - dolphin - seal - animal 49 91_whale_porpoise_dolphin_seal
92 yemen - houthis - hadi - houthi - saudi 49 92_yemen_houthis_hadi_houthi
93 eurozone - ecb - bank - qe - inflation 49 93_eurozone_ecb_bank_qe
94 fracking - shale - gas - cuadrilla - energy 48 94_fracking_shale_gas_cuadrilla
95 museum - gallery - castle - museums - art 48 95_museum_gallery_castle_museums
96 rate - inflation - growth - price - economist 48 96_rate_inflation_growth_price
97 terrorism - iqbal - ziamani - heard - hussain 48 97_terrorism_iqbal_ziamani_heard
98 abortion - woman - pregnancy - northern - ireland 47 98_abortion_woman_pregnancy_northern
99 antibiotic - resistance - vaccine - infection - disease 46 99_antibiotic_resistance_vaccine_infection
100 smoking - ecigarettes - tobacco - smoker - smoke 44 100_smoking_ecigarettes_tobacco_smoker
101 refugee - asylum - seeker - refugees - syrian 43 101_refugee_asylum_seeker_refugees
102 car - ford - plant - nissan - engine 43 102_car_ford_plant_nissan
103 syria - iraq - strike - mps - military 43 103_syria_iraq_strike_mps
104 ice - climate - warming - glacier - temperature 43 104_ice_climate_warming_glacier
105 wasps - replacements - capt - gloucester - try 42 105_wasps_replacements_capt_gloucester
106 vr - game - headset - console - nintendo 42 106_vr_game_headset_console
107 farc - peace - rebel - colombian - santos 42 107_farc_peace_rebel_colombian
108 wales - coleman - bale - belgium - tournament 42 108_wales_coleman_bale_belgium
109 tax - credit - universal - income - cut 41 109_tax_credit_universal_income
110 ireland - border - northern - brexit - eu 38 110_ireland_border_northern_brexit
111 inquest - connor - ira - soldier - officer 37 111_inquest_connor_ira_soldier
112 vw - emission - diesel - volkswagen - car 37 112_vw_emission_diesel_volkswagen
113 reactor - nuclear - radiation - radioactive - plant 37 113_reactor_nuclear_radiation_radioactive
114 ebola - outbreak - liberia - leone - sierra 37 114_ebola_outbreak_liberia_leone
115 mayor - council - devolution - combined - authority 36 115_mayor_council_devolution_combined
116 rousseff - petrobras - impeachment - temer - brazils 36 116_rousseff_petrobras_impeachment_temer
117 auschwitz - jews - nazi - camp - holocaust 36 117_auschwitz_jews_nazi_camp
118 fifa - blatter - platini - fifas - sepp 36 118_fifa_blatter_platini_fifas
119 farmer - milk - farmers - dairy - farm 36 119_farmer_milk_farmers_dairy
120 bosnian - kosovo - serbia - montenegro - serbs 35 120_bosnian_kosovo_serbia_montenegro
121 drug - cannabis - heroin - substance - drugs 35 121_drug_cannabis_heroin_substance
122 driving - crash - causing - court - road 35 122_driving_crash_causing_court
123 zika - virus - mosquito - microcephaly - spread 34 123_zika_virus_mosquito_microcephaly
124 stolen - robbery - dark - theft - det 34 124_stolen_robbery_dark_theft
125 aircraft - spitfire - raf - flying - vulcan 34 125_aircraft_spitfire_raf_flying
126 russia - fan - fifa - racism - football 33 126_russia_fan_fifa_racism
127 whyte - rangers - findlay - ticketus - hmrc 33 127_whyte_rangers_findlay_ticketus
128 wage - pay - minimum - rate - unemployment 32 128_wage_pay_minimum_rate
129 picture - please - englands - pictures - englandsbigpicture 32 129_picture_please_englands_pictures
130 fire - cladding - tower - grenfell - block 32 130_fire_cladding_tower_grenfell
131 speed - driver - camera - speeding - road 32 131_speed_driver_camera_speeding
132 train - rail - raib - crash - driver 31 132_train_rail_raib_crash
133 labor - turnbull - abbott - lyons - australian 31 133_labor_turnbull_abbott_lyons
134 music - spotify - streaming - youtube - artist 31 134_music_spotify_streaming_youtube
135 nama - pimco - cerberus - cushnahan - namas 30 135_nama_pimco_cerberus_cushnahan
136 drone - aircraft - drones - uavs - aviation 30 136_drone_aircraft_drones_uavs
137 catalan - rajoy - spanish - eta - catalonia 30 137_catalan_rajoy_spanish_eta
138 charity - kids - batmanghelidjh - fundraising - yentob 30 138_charity_kids_batmanghelidjh_fundraising
139 hillsborough - disaster - inquest - duckenfield - 1989 29 139_hillsborough_disaster_inquest_duckenfield
140 cuba - cuban - castro - cubans - cubas 29 140_cuba_cuban_castro_cubans
141 yingluck - thaksin - thai - shinawatra - thailands 29 141_yingluck_thaksin_thai_shinawatra
142 calais - migrant - eurotunnel - lorry - french 28 142_calais_migrant_eurotunnel_lorry
143 extremism - extremist - prevent - tpims - terrorism 28 143_extremism_extremist_prevent_tpims
144 trudeau - canadian - canada - trudeaus - canadians 28 144_trudeau_canadian_canada_trudeaus
145 ferry - condor - vessel - ferries - cowes 27 145_ferry_condor_vessel_ferries
146 lottery - gambling - jackpot - ticket - euromillions 26 146_lottery_gambling_jackpot_ticket
147 bank - growth - inflation - forecast - rate 26 147_bank_growth_inflation_forecast
148 organ - transplant - donor - donation - blood 26 148_organ_transplant_donor_donation
149 nba - cavaliers - curry - cleveland - warriors 26 149_nba_cavaliers_curry_cleveland
150 camp - unaccompanied - calais - child - migrant 25 150_camp_unaccompanied_calais_child
151 germany - asylum - refugee - german - cologne 25 151_germany_asylum_refugee_german
152 marriage - gay - samesex - ashers - equality 25 152_marriage_gay_samesex_ashers
153 nauru - asylum - australia - manus - seeker 25 153_nauru_asylum_australia_manus
154 oil - barrel - price - opec - prices 25 154_oil_barrel_price_opec
155 pistorius - steenkamp - reeva - toilet - intruder 25 155_pistorius_steenkamp_reeva_toilet
156 obesity - overweight - obese - child - health 25 156_obesity_overweight_obese_child
157 swansea - circuit - wales - welsh - skates 24 157_swansea_circuit_wales_welsh
158 england - hodgson - rooney - kane - englands 24 158_england_hodgson_rooney_kane
159 lukaku - bielsa - chelsea - mourinho - club 24 159_lukaku_bielsa_chelsea_mourinho
160 dinosaur - fossil - feather - frog - egg 24 160_dinosaur_fossil_feather_frog
161 scheme - foster - rhi - dup - subsidy 24 161_scheme_foster_rhi_dup
162 bhs - pension - scheme - chappell - ppf 24 162_bhs_pension_scheme_chappell
163 crash - plane - a27 - air - shoreham 23 163_crash_plane_a27_air
164 libor - hayes - bank - hsbc - rate 23 164_libor_hayes_bank_hsbc
165 duterte - philippines - drug - oil - palm 23 165_duterte_philippines_drug_oil
166 arrested - suspicion - terrorism - police - aged 23 166_arrested_suspicion_terrorism_police
167 sugar - drink - food - fruit - sugary 23 167_sugar_drink_food_fruit
168 africans - africa - selection - photo - baya 23 168_africans_africa_selection_photo
169 cruise - hms - harbour - ship - queen 23 169_cruise_hms_harbour_ship
170 trade - tpp - lumber - canada - china 23 170_trade_tpp_lumber_canada
171 ivory - elephant - rhino - poaching - horn 23 171_ivory_elephant_rhino_poaching
172 nfl - patriots - yall - quarterback - touchdown 22 172_nfl_patriots_yall_quarterback
173 horsemeat - product - beef - food - cheese 21 173_horsemeat_product_beef_food
174 plane - mh370 - flight - search - debris 21 174_plane_mh370_flight_search
175 everest - climber - mountain - summit - sherpa 20 175_everest_climber_mountain_summit
176 robot - ai - robots - machine - human 20 176_robot_ai_robots_machine
177 pension - advice - annuity - pot - pensions 20 177_pension_advice_annuity_pot
178 flight - airport - passenger - plane - aircraft 20 178_flight_airport_passenger_plane
179 solar - impulse - leg - piccard - plane 20 179_solar_impulse_leg_piccard
180 airbus - airline - aircraft - a380 - airlines 20 180_airbus_airline_aircraft_a380
181 rohingya - rakhine - myanmar - rohingyas - buddhist 20 181_rohingya_rakhine_myanmar_rohingyas
182 suu - kyi - nld - aung - myanmar 20 182_suu_kyi_nld_aung
183 women - 100women - 100 - inspirational - stereotype 20 183_women_100women_100_inspirational
184 republic - ireland - poland - hungary - georgia 20 184_republic_ireland_poland_hungary
185 science - research - ukri - funding - scientific 20 185_science_research_ukri_funding
186 erdogan - turkish - gulen - coup - turkey 19 186_erdogan_turkish_gulen_coup
187 manchester - attack - exercise - security - terror 19 187_manchester_attack_exercise_security
188 esports - sport - app - bbc - live 19 188_esports_sport_app_bbc
189 breivik - oslo - breiviks - utoeya - norway 18 189_breivik_oslo_breiviks_utoeya
190 birth - teenage - baby - mental - infant 18 190_birth_teenage_baby_mental
191 fraud - scam - account - bank - scams 18 191_fraud_scam_account_bank
192 alzheimers - dementia - disease - brain - iodine 18 192_alzheimers_dementia_disease_brain
193 ducati - yamaha - marquez - spa - rossi 17 193_ducati_yamaha_marquez_spa
194 nsa - snowden - intelligence - cia - us 17 194_nsa_snowden_intelligence_cia
195 pkk - kurdish - turkish - turkey - kurds 17 195_pkk_kurdish_turkish_turkey
196 ban - order - trump - us - trumps 17 196_ban_order_trump_us
197 tree - ash - dieback - woodland - disease 17 197_tree_ash_dieback_woodland
198 mine - miner - miners - coal - underground 17 198_mine_miner_miners_coal
199 eu - financial - business - european - london 16 199_eu_financial_business_european
200 romania - ponta - romanian - romanias - decree 16 200_romania_ponta_romanian_romanias
201 rugby - season - tuitavake - nrl - pirates 16 201_rugby_season_tuitavake_nrl
202 unite - union - strike - action - pay 16 202_unite_union_strike_action
203 ashley - sports - direct - shirebrook - warehouse 16 203_ashley_sports_direct_shirebrook
204 giants - braehead - period - flyers - stars 16 204_giants_braehead_period_flyers
205 pfi - swinney - scottish - council - government 16 205_pfi_swinney_scottish_council
206 cow - beef - slaughter - meat - crop 15 206_cow_beef_slaughter_meat
207 ford - carmaker - fiat - gm - chrysler 15 207_ford_carmaker_fiat_gm
208 ilott - court - mrs - judge - mother 15 208_ilott_court_mrs_judge
209 cosby - cosbys - constand - comedian - drugged 14 209_cosby_cosbys_constand_comedian
210 tv - medium - internetworldstats - jazeera - network 14 210_tv_medium_internetworldstats_jazeera
211 ira - psni - ombudsman - kingsmills - wallace 14 211_ira_psni_ombudsman_kingsmills
212 playback - supported - media - device - guide 14 212_playback_supported_media_device
213 argentina - ghana - bosnia - herzegovina - croatia 13 213_argentina_ghana_bosnia_herzegovina
214 syria - brekke - ulhaq - muthana - faulkner 13 214_syria_brekke_ulhaq_muthana
215 care - social - council - cap - cost 13 215_care_social_council_cap
216 loneliness - veteran - veterans - mental - dyslexia 13 216_loneliness_veteran_veterans_mental
217 hinkley - edf - nuclear - plant - project 13 217_hinkley_edf_nuclear_plant
218 assange - ecuador - snowden - wikileaks - sweden 13 218_assange_ecuador_snowden_wikileaks
219 faw - cardiff - stadium - wales - champions 13 219_faw_cardiff_stadium_wales
220 prediction - lawros - lawro - match - correct 13 220_prediction_lawros_lawro_match
221 russian - putin - russia - language - trump 13 221_russian_putin_russia_language
222 funeral - burial - cremation - cemetery - crematorium 13 222_funeral_burial_cremation_cemetery
223 bevan - hospital - baby - borasinski - lambert 13 223_bevan_hospital_baby_borasinski
224 badger - tb - cull - cattle - bovine 12 224_badger_tb_cull_cattle
225 swansea - sunderland - swans - guidolin - swanseas 12 225_swansea_sunderland_swans_guidolin
226 afd - merkels - cdu - merkel - spd 12 226_afd_merkels_cdu_merkel
227 sousse - attack - tunisia - tunisian - rezgui 12 227_sousse_attack_tunisia_tunisian
228 porn - name - venables - image - fogle 12 228_porn_name_venables_image
229 childcare - nursery - carers - fouryearolds - child 12 229_childcare_nursery_carers_fouryearolds
230 chinese - film - hollywood - wanda - movie 12 230_chinese_film_hollywood_wanda
231 fgm - genital - girl - mutilation - nagarwala 12 231_fgm_genital_girl_mutilation
232 scourfield - mills - fraud - duffin - fraudulent 12 232_scourfield_mills_fraud_duffin
233 mexico - mexicans - trump - mexican - wall 12 233_mexico_mexicans_trump_mexican
234 palmyra - temple - ancient - ruin - cultural 11 234_palmyra_temple_ancient_ruin
235 factory - garment - bangladesh - worker - rana 11 235_factory_garment_bangladesh_worker
236 rink - muirhead - sweden - medal - muirheads 11 236_rink_muirhead_sweden_medal
237 hurricane - storm - texas - tornado - category 11 237_hurricane_storm_texas_tornado
238 shahid - sabri - shahids - shah - pakistan 11 238_shahid_sabri_shahids_shah
239 chapecoense - sudamericana - copa - plane - crash 11 239_chapecoense_sudamericana_copa_plane
240 bee - hornet - neonicotinoids - hive - tunibee 10 240_bee_hornet_neonicotinoids_hive
241 malaria - virus - anthrax - parasite - infection 10 241_malaria_virus_anthrax_parasite
242 beer - brewdog - ab - brewery - inbev 10 242_beer_brewdog_ab_brewery
243 tesla - teslas - musk - electric - model 10 243_tesla_teslas_musk_electric
244 borrowing - budget - obr - forecast - debt 10 244_borrowing_budget_obr_forecast
245 russian - plane - missile - mh17 - jit 10 245_russian_plane_missile_mh17
246 a48 - traffic - morriston - reopened - carriageway 10 246_a48_traffic_morriston_reopened
247 army - mod - reserve - defence - recruitment 9 247_army_mod_reserve_defence
248 driving - driver - dixon - wheel - alcohol 9 248_driving_driver_dixon_wheel
249 rahman - hamlets - lutfur - mawrey - mayor 9 249_rahman_hamlets_lutfur_mawrey
250 newsquest - johnston - editorial - herald - newspaper 9 250_newsquest_johnston_editorial_herald
251 gerwen - wade - van - anderson - wright 9 251_gerwen_wade_van_anderson
252 clown - clowning - name - surname - clowns 9 252_clown_clowning_name_surname
253 cyberbullying - bullying - child - online - bully 9 253_cyberbullying_bullying_child_online
254 potters - grabban - bournemouth - stoke - martina 8 254_potters_grabban_bournemouth_stoke
255 note - banknote - polymer - bank - notes 8 255_note_banknote_polymer_bank
256 alcohol - drink - drinking - unit - alcoholrelated 8 256_alcohol_drink_drinking_unit
257 expedition - polar - scotts - antarctic - pole 8 257_expedition_polar_scotts_antarctic
258 mps - snp - bill - scotland - commons 8 258_mps_snp_bill_scotland
259 pte - vallely - deepcut - inquest - wound 8 259_pte_vallely_deepcut_inquest
260 beach - bathing - water - beaches - quality 8 260_beach_bathing_water_beaches
261 fake - news - yahoo - facebook - micro 8 261_fake_news_yahoo_facebook
262 ad - google - berec - googles - adblocking 7 262_ad_google_berec_googles
263 tram - croydon - addington - seary - chinnery 7 263_tram_croydon_addington_seary
264 berlusconi - fascist - italian - renzi - monti 7 264_berlusconi_fascist_italian_renzi
265 coulson - hacking - phone - news - voicemail 7 265_coulson_hacking_phone_news
266 advice - disability - pip - disabled - career 7 266_advice_disability_pip_disabled
267 cbos - legal - pspo - antisocial - behaviour 7 267_cbos_legal_pspo_antisocial
268 coal - mine - kellingley - daw - colliery 7 268_coal_mine_kellingley_daw
269 villa - aston - everton - funes - gestede 7 269_villa_aston_everton_funes
270 lifestart - hazel - debbie - loreto - clare 7 270_lifestart_hazel_debbie_loreto
271 humza - firearm - chauhan - gun - rai 6 271_humza_firearm_chauhan_gun
272 trollope - cardiff - bluebirds - whittingham - morrison 6 272_trollope_cardiff_bluebirds_whittingham
273 shepherd - monoxide - christi - boiler - fankhauser 6 273_shepherd_monoxide_christi_boiler
274 hp - kodak - hewlettpackard - fujitsu - fitbit 6 274_hp_kodak_hewlettpackard_fujitsu
275 xinjiang - cu - kunming - uighur - rua 6 275_xinjiang_cu_kunming_uighur
276 monis - australia - australian - sydney - sharrouf 6 276_monis_australia_australian_sydney
277 inquiry - emmerson - inquirys - abuse - jay 6 277_inquiry_emmerson_inquirys_abuse
278 burkini - dufourmantelle - headscarf - french - secularism 6 278_burkini_dufourmantelle_headscarf_french
279 argentina - fernandez - macri - hedge - argentinas 6 279_argentina_fernandez_macri_hedge
280 essar - ship - furnace - ruihai - xinhua 6 280_essar_ship_furnace_ruihai
281 distillery - whisky - dairy - tullibardine - ardbeg 6 281_distillery_whisky_dairy_tullibardine
282 mccallion - kendrick - defendant - sultana - solicitor 6 282_mccallion_kendrick_defendant_sultana
283 execution - lethal - drug - inmate - midazolam 6 283_execution_lethal_drug_inmate
284 equality - lgbti - prejudice - register - constance 6 284_equality_lgbti_prejudice_register
285 facebook - user - instagram - systrom - clip 6 285_facebook_user_instagram_systrom
286 tax - cayman - havens - company - multinationals 6 286_tax_cayman_havens_company
287 rig - transocean - hawk - dalmore - aground 6 287_rig_transocean_hawk_dalmore
288 richardsonwalsh - gb - netted - netherlands - equalised 6 288_richardsonwalsh_gb_netted_netherlands
289 vale - smurthwaite - ribeiro - page - norman 6 289_vale_smurthwaite_ribeiro_page
290 bma - junior - doctor - jdc - contract 6 290_bma_junior_doctor_jdc
291 hip - prasad - clodagh - lockedin - spine 5 291_hip_prasad_clodagh_lockedin
292 stonehaven - eccles - wyndthorpe - cullompton - inchmichael 5 292_stonehaven_eccles_wyndthorpe_cullompton
293 ngoepe - pitcher - cubs - bumgarner - giants 5 293_ngoepe_pitcher_cubs_bumgarner
294 mowbray - pieters - hogan - league - forestieri 5 294_mowbray_pieters_hogan_league
295 1500 - gmt - ham - sunderland - preston 5 295_1500_gmt_ham_sunderland
296 vocational - experience - unemployment - placement - work 5 296_vocational_experience_unemployment_placement
297 mcclaren - loan - blues - ince - club 5 297_mcclaren_loan_blues_ince
298 ambulance - pedestrians - vehicle - crew - kinfauns 5 298_ambulance_pedestrians_vehicle_crew
299 ride - merlin - smiler - alton - carriage 5 299_ride_merlin_smiler_alton
300 ski - snowsports - cairngorm - snow - mountain 5 300_ski_snowsports_cairngorm_snow
301 mossack - fonseca - offshore - document - tax 5 301_mossack_fonseca_offshore_document
302 rape - child - exemption - thewliss - clause 5 302_rape_child_exemption_thewliss
303 udinese - dijk - defender - season - battocchio 5 303_udinese_dijk_defender_season
304 hatton - jewellery - burglary - biggs - burglars 5 304_hatton_jewellery_burglary_biggs
305 cornell - conley - mohamud - allegedly - raoufi 5 305_cornell_conley_mohamud_allegedly
306 balloon - konyukhov - landed - glow - connor 5 306_balloon_konyukhov_landed_glow
307 crickitt - gbangbola - saunders - leahys - insulin 5 307_crickitt_gbangbola_saunders_leahys
308 water - pipeline - thames - river - sewage 5 308_water_pipeline_thames_river
309 appeal - dennehy - boota - sinclair - sentencing 5 309_appeal_dennehy_boota_sinclair
310 cottrez - gbangbola - sunaria - zanes - inquest 5 310_cottrez_gbangbola_sunaria_zanes

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
Downloads last month
11
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.