xsum_6789_5000000_2500000_v1_50topics_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_50topics_train")

topic_model.get_topic_info()

Topic overview

• Number of topics: 50
• Number of training documents: 204045

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - mr - would - one - year	6	-1_said_mr_would_one
0	win - game - half - second - right	120934	0_win_game_half_second
1	said - would - labour - eu - party	18917	1_said_would_labour_eu
2	said - police - mr - court - would	14269	2_said_police_mr_court
3	mr - president - said - government - us	12871	3_mr_president_said_government
4	bank - company - sale - said - year	9344	4_bank_company_sale_said
5	fire - said - flood - people - water	2912	5_fire_said_flood_people
6	airport - flight - space - plane - aircraft	2642	6_airport_flight_space_plane
7	trump - mr - us - clinton - said	2601	7_trump_mr_us_clinton
8	energy - oil - rate - growth - price	2301	8_energy_oil_rate_growth
9	sea - water - ship - said - coastguard	2183	9_sea_water_ship_said
10	dog - animal - bird - said - zoo	1899	10_dog_animal_bird_said
11	president - fifa - mr - government - cuba	1707	11_president_fifa_mr_government
12	film - bbc - actor - star - show	1665	12_film_bbc_actor_star
13	drug - alcohol - smoking - pollution - health	1340	13_drug_alcohol_smoking_pollution
14	music - album - song - band - chart	1193	14_music_album_song_band
15	virus - ebola - health - infection - vaccine	827	15_virus_ebola_health_infection
16	yn - ar - wedi - ei - bod	765	16_yn_ar_wedi_ei
17	robot - car - research - technology - science	560	17_robot_car_research_technology
18	india - indian - delhi - indias - modi	469	18_india_indian_delhi_indias
19	found - museum - site - fossil - roman	431	19_found_museum_site_fossil
20	church - bishop - pope - vatican - cardinal	429	20_church_bishop_pope_vatican
21	australia - australian - mr - nauru - prime	381	21_australia_australian_mr_nauru
22	unsupported - updated - playback - device - media	342	22_unsupported_updated_playback_device
23	prince - royal - queen - duchess - duke	293	23_prince_royal_queen_duchess
24	marriage - gay - law - samesex - transgender	266	24_marriage_gay_law_samesex
25	updated - bst - gmt - last - 2017	235	25_updated_bst_gmt_last
26	food - product - meat - horsemeat - cheese	232	26_food_product_meat_horsemeat
27	woman - fashion - dress - women - wear	209	27_woman_fashion_dress_women
28	book - novel - author - prize - writer	202	28_book_novel_author_prize
29	mountain - avalanche - climber - everest - snow	201	29_mountain_avalanche_climber_everest
30	trident - defence - submarine - nuclear - army	180	30_trident_defence_submarine_nuclear
31	christmas - bell - cake - poppy - minster	152	31_christmas_bell_cake_poppy
32	cosby - clown - constand - mr - cosbys	144	32_cosby_clown_constand_mr
33	water - utilities - customer - company - said	125	33_water_utilities_customer_company
34	sleep - suicide - life - people - health	118	34_sleep_suicide_life_people
35	flag - confederate - white - university - statue	115	35_flag_confederate_white_university
36	nba - warriors - lakers - cavaliers - game	109	36_nba_warriors_lakers_cavaliers
37	picture - scotlandpicturesbbccouk - bbcscotlandpics - photo - selection	98	37_picture_scotlandpicturesbbccouk_bbcscotlandpics_photo
38	flag - emojis - deaf - emoji - language	89	38_flag_emojis_deaf_emoji
39	ring - diamond - jewellery - carat - jewel	65	39_ring_diamond_jewellery_carat
40	pokemon - game - go - ai - player	49	40_pokemon_game_go_ai
41	takata - airbags - recall - honda - airbag	37	41_takata_airbags_recall_honda
42	follow - - - -	35	42_follow___
43	depp - joyce - dog - boo - pistol	29	43_depp_joyce_dog_boo
44	leaguebyleague - list - managerial - below - appear	26	44_leaguebyleague_list_managerial_below
45	name - top - girls - boys - boy	17	45_name_top_girls_boys
46	film - potter - scotland - beasts - grindelwald	15	46_film_potter_scotland_beasts
47	balcony - irish - berkeley - student - donohoe	10	47_balcony_irish_berkeley_student
48	flower - garden - flowered - botanic - arum	6	48_flower_garden_flowered_botanic

Training hyperparameters

• calculate_probabilities: True
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 50
• 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