xsum_6789_5000000_2500000_v1_150topics_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_5000000_2500000_v1_150topics_train")

topic_model.get_topic_info()

Topic overview

• Number of topics: 150
• Number of training documents: 204045

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - year - one - mr - also	5	-1_said_year_one_mr
0	half - win - kick - foul - game	120934	0_half_win_kick_foul
1	labour - eu - party - uk - vote	12329	1_labour_eu_party_uk
2	race - champion - world - title - fight	7075	2_race_champion_world_title
3	school - education - health - patient - nhs	5962	3_school_education_health_patient
4	police - murder - court - man - mr	4410	4_police_murder_court_man
5	rail - train - transport - driver - road	4066	5_rail_train_transport_driver
6	al - syria - syrian - attack - us	3623	6_al_syria_syrian_attack
7	prison - police - inquiry - abuse - court	3574	7_prison_police_inquiry_abuse
8	africa - african - nigeria - president - boko	2827	8_africa_african_nigeria_president
9	fire - blaze - building - firefighter - smoke	1675	9_fire_blaze_building_firefighter
10	russia - russian - ukraine - putin - president	1460	10_russia_russian_ukraine_putin
11	coastguard - fish - water - rescue - sea	1341	11_coastguard_fish_water_rescue
12	dog - animal - zoo - cat - rspca	1312	12_dog_animal_zoo_cat
13	sale - company - share - firm - apple	1302	13_sale_company_share_firm
14	data - security - facebook - user - google	1224	14_data_security_facebook_user
15	energy - oil - gas - climate - price	1084	15_energy_oil_gas_climate
16	space - earth - planet - mission - satellite	1072	16_space_earth_planet_mission
17	cuba - venezuela - president - farc - maduro	1057	17_cuba_venezuela_president_farc
18	art - council - library - building - museum	1040	18_art_council_library_building
19	ireland - dup - northern - sinn - féin	1020	19_ireland_dup_northern_sinn
20	bank - tax - fraud - money - bitcoin	1008	20_bank_tax_fraud_money
21	flood - flooding - water - rain - storm	959	21_flood_flooding_water_rain
22	trump - clinton - mr - republican - president	955	22_trump_clinton_mr_republican
23	film - actor - star - show - best	920	23_film_actor_star_show
24	plane - aircraft - flight - drone - pilot	918	24_plane_aircraft_flight_drone
25	korea - north - china - korean - kim	867	25_korea_north_china_korean
26	music - album - song - band - singer	839	26_music_album_song_band
27	virus - ebola - vaccine - infection - disease	827	27_virus_ebola_vaccine_infection
28	abortion - hospital - care - death - baby	765	28_abortion_hospital_care_death
29	rate - growth - economy - inflation - bank	759	29_rate_growth_economy_inflation
30	airport - airline - heathrow - passenger - runway	727	30_airport_airline_heathrow_passenger
31	yn - mae - ar - wedi - ei	653	31_yn_mae_ar_wedi
32	thailand - myanmar - thai - kyi - suu	560	32_thailand_myanmar_thai_kyi
33	attack - paris - french - france - police	542	33_attack_paris_french_france
34	migrant - refugee - asylum - eu - europe	535	34_migrant_refugee_asylum_eu
35	ship - ferry - vessel - hms - navy	522	35_ship_ferry_vessel_hms
36	drug - cannabis - heroin - drugs - cocaine	466	36_drug_cannabis_heroin_drugs
37	doping - athlete - iaaf - olympic - wada	449	37_doping_athlete_iaaf_olympic
38	bbc - 00 - radio - tv - news	442	38_bbc_00_radio_tv
39	pte - soldier - cpl - war - inquest	422	39_pte_soldier_cpl_war
40	india - modi - delhi - bjp - indian	415	40_india_modi_delhi_bjp
41	bird - bee - rspb - wildlife - birds	398	41_bird_bee_rspb_wildlife
42	smoking - pollution - air - tobacco - cigarettes	394	42_smoking_pollution_air_tobacco
43	church - bishop - pope - vatican - cardinal	393	43_church_bishop_pope_vatican
44	greece - eurozone - greek - bank - ecb	381	44_greece_eurozone_greek_bank
45	museum - roman - archaeologist - site - found	335	45_museum_roman_archaeologist_site
46	alcohol - drink - whisky - drinking - wine	320	46_alcohol_drink_whisky_drinking
47	australia - labor - nauru - australian - turnbull	307	47_australia_labor_nauru_australian
48	car - vw - emission - volkswagen - diesel	299	48_car_vw_emission_volkswagen
49	unsupported - updated - playback - device - media	294	49_unsupported_updated_playback_device
50	robot - car - vehicle - technology - computer	293	50_robot_car_vehicle_technology
51	broadband - bt - ofcom - mobile - openreach	257	51_broadband_bt_ofcom_mobile
52	prince - queen - duchess - royal - duke	253	52_prince_queen_duchess_royal
53	school - pupil - bullying - teacher - student	250	53_school_pupil_bullying_teacher
54	festival - event - yorkshire - edinburgh - tour	241	54_festival_event_yorkshire_edinburgh
55	updated - gmt - bst - 2017 - last	240	55_updated_gmt_bst_2017
56	fifa - blatter - platini - football - swiss	225	56_fifa_blatter_platini_football
57	food - product - meat - horsemeat - nestle	224	57_food_product_meat_horsemeat
58	game - console - nintendo - vr - oculus	209	58_game_console_nintendo_vr
59	book - novel - author - prize - writer	208	59_book_novel_author_prize
60	welsh - language - ashley - sports - sport	201	60_welsh_language_ashley_sports
61	manchester - concert - abedi - grande - ariana	199	61_manchester_concert_abedi_grande
62	rousseff - lula - brazil - petrobras - temer	196	62_rousseff_lula_brazil_petrobras
63	charity - kids - batmanghelidjh - fundraising - service	185	63_charity_kids_batmanghelidjh_fundraising
64	mountain - avalanche - everest - climber - snow	185	64_mountain_avalanche_everest_climber
65	fgm - trafficking - slavery - sex - victim	180	65_fgm_trafficking_slavery_sex
66	trade - tpp - obamacare - ceta - us	159	66_trade_tpp_obamacare_ceta
67	assange - wikileaks - snowden - manning - ecuador	152	67_assange_wikileaks_snowden_manning
68	trident - defence - nuclear - submarine - army	145	68_trident_defence_nuclear_submarine
69	berlusconi - italy - italian - regeni - renzi	135	69_berlusconi_italy_italian_regeni
70	choi - park - ms - samsung - lee	128	70_choi_park_ms_samsung
71	mayor - ford - council - rahman - devolution	126	71_mayor_ford_council_rahman
72	mine - miner - coal - mining - pit	126	72_mine_miner_coal_mining
73	ice - antarctic - sea - arctic - ocean	126	73_ice_antarctic_sea_arctic
74	transgender - abortion - law - gay - marriage	121	74_transgender_abortion_law_gay
75	gambling - lottery - jackpot - ticket - betting	120	75_gambling_lottery_jackpot_ticket
76	gay - marriage - same - sex - ashers	119	76_gay_marriage_same_sex
77	flag - confederate - white - university - statue	115	77_flag_confederate_white_university
78	fossil - dinosaur - human - modern - homo	109	78_fossil_dinosaur_human_modern
79	science - research - graphene - prof - prize	109	79_science_research_graphene_prof
80	nuclear - japan - reactor - radiation - plant	106	80_nuclear_japan_reactor_radiation
81	tree - ash - trees - woodland - dieback	105	81_tree_ash_trees_woodland
82	trump - golf - crofting - turnberry - hie	104	82_trump_golf_crofting_turnberry
83	doping - armstrong - cycling - sharapova - meldonium	101	83_doping_armstrong_cycling_sharapova
84	picture - scotlandpictures - bbcscotlandpics - photo - selection	100	84_picture_scotlandpictures_bbcscotlandpics_photo
85	water - utilities - customer - cryptosporidium - company	89	85_water_utilities_customer_cryptosporidium
86	christmas - cake - santa - going - toy	89	86_christmas_cake_santa_going
87	fashion - dress - vogue - wear - designer	82	87_fashion_dress_vogue_wear
88	nba - lakers - cavaliers - warriors - bryant	82	88_nba_lakers_cavaliers_warriors
89	woman - women - female - gender - 100	74	89_woman_women_female_gender
90	robot - ant - prof - insect - robots	74	90_robot_ant_prof_insect
91	cosby - constand - mueller - swift - lawyer	68	91_cosby_constand_mueller_swift
92	note - polymer - bank - banknote - coin	66	92_note_polymer_bank_banknote
93	argentina - argentine - falklands - falkland - islands	63	93_argentina_argentine_falklands_falkland
94	suicide - happiness - expectancy - life - age	62	94_suicide_happiness_expectancy_life
95	volcano - ash - eruption - earthquake - bgs	61	95_volcano_ash_eruption_earthquake
96	nfl - patriots - brady - quarterback - bowl	60	96_nfl_patriots_brady_quarterback
97	light - lighting - sky - dark - clock	60	97_light_lighting_sky_dark
98	ring - diamond - jewellery - carat - jewel	52	98_ring_diamond_jewellery_carat
99	pipeline - dakota - oil - sioux - keystone	49	99_pipeline_dakota_oil_sioux
100	bell - minster - ringers - ringing - imber	49	100_bell_minster_ringers_ringing
101	mail - royal - post - parcel - delivery	47	101_mail_royal_post_parcel
102	breastfeeding - advert - body - asa - image	47	102_breastfeeding_advert_body_asa
103	sleep - clock - screen - hour - internet	46	103_sleep_clock_screen_hour
104	island - islands - prime - becomes - minister	44	104_island_islands_prime_becomes
105	qatar - worker - garment - factory - bangladesh	43	105_qatar_worker_garment_factory
106	laser - weapon - firearm - pilot - airgun	41	106_laser_weapon_firearm_pilot
107	palmyra - ancient - syrian - site - cultural	39	107_palmyra_ancient_syrian_site
108	pokemon - game - ai - go - alphago	39	108_pokemon_game_ai_go
109	flag - emojis - emoji - unicode - design	37	109_flag_emojis_emoji_unicode
110	takata - airbags - recall - airbag - honda	37	110_takata_airbags_recall_airbag
111	clown - clowns - craze - creepy - dressed	35	111_clown_clowns_craze_creepy
112	india - film - indian - bollywood - food	34	112_india_film_indian_bollywood
113	airbnb - bite - homeless - social - littlejohn	33	113_airbnb_bite_homeless_social
114	follow - - - -	33	114_follow___
115	quantum - computing - photon - qubits - computer	29	115_quantum_computing_photon_qubits
116	bundy - federal - refuge - rancher - sweat	26	116_bundy_federal_refuge_rancher
117	cubs - baseball - series - curse - mets	25	117_cubs_baseball_series_curse
118	india - indian - china - modi - chinese	24	118_india_indian_china_modi
119	sinkhole - hole - florida - fontmell - collapse	24	119_sinkhole_hole_florida_fontmell
120	pitch - fixture - referee - rain - postponed	24	120_pitch_fixture_referee_rain
121	bloodhound - speed - car - record - rocket	24	121_bloodhound_speed_car_record
122	malala - pakistan - yousafzai - taliban - education	24	122_malala_pakistan_yousafzai_taliban
123	depp - joyce - dog - australia - boo	22	123_depp_joyce_dog_australia
124	list - managerial - below - league - by	18	124_list_managerial_below_league
125	warrior - joint - unmanned - exercise - navy	17	125_warrior_joint_unmanned_exercise
126	polanski - extradition - polish - geimer - poland	17	126_polanski_extradition_polish_geimer
127	deaf - language - bsl - sign - hearing	16	127_deaf_language_bsl_sign
128	name - boys - girls - boy - top	15	128_name_boys_girls_boy
129	poppy - war - weeping - cummins - 888	15	129_poppy_war_weeping_cummins
130	tattoo - tattooists - tattooing - piercing - tattooist	15	130_tattoo_tattooists_tattooing_piercing
131	balakrishnan - commune - cult - aravindan - woman	13	131_balakrishnan_commune_cult_aravindan
132	visa - brain - cothill - mrs - family	13	132_visa_brain_cothill_mrs
133	battery - lithium - ion - batteries - cathode	13	133_battery_lithium_ion_batteries
134	peachey - tip - calendar - finance - updated	12	134_peachey_tip_calendar_finance
135	emperor - akihito - prince - throne - imperial	12	135_emperor_akihito_prince_throne
136	dog - personality - animal - wolf - human	11	136_dog_personality_animal_wolf
137	decay - dental - tooth - teeth - oral	11	137_decay_dental_tooth_teeth
138	puerto - princess - urdangarin - rico - cristina	10	138_puerto_princess_urdangarin_rico
139	pitt - jolie - paltrow - married - divorce	10	139_pitt_jolie_paltrow_married
140	minnock - ethan - wildblood - father - court	8	140_minnock_ethan_wildblood_father
141	breaking - bbcbreaking - alert - fullest - via	8	141_breaking_bbcbreaking_alert_fullest
142	balcony - berkeley - irish - student - donohoe	7	142_balcony_berkeley_irish_student
143	flower - garden - flowered - botanic - arum	6	143_flower_garden_flowered_botanic
144	potter - beasts - grindelwald - dumbledore - film	6	144_potter_beasts_grindelwald_dumbledore
145	canal - waterway - oakham - towpath - lock	5	145_canal_waterway_oakham_towpath
146	carta - magna - 1215 - king - charter	5	146_carta_magna_1215_king
147	mccollum - reid - peru - cocaine - lima	5	147_mccollum_reid_peru_cocaine
148	film - scotland - location - outlander - movie	5	148_film_scotland_location_outlander

Training hyperparameters

• calculate_probabilities: True
• language: None
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 150
• 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