KingKazma's picture
Add BERTopic model
d706015
metadata
tags:
  - bertopic
library_name: bertopic
pipeline_tag: text-classification

xsum_123_3000_1500_validation

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_123_3000_1500_validation")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 27
  • Number of training documents: 1500
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 said - mr - would - also - year 5 -1_said_mr_would_also
0 police - said - court - mr - found 654 0_police_said_court_mr
1 said - council - site - would - development 101 1_said_council_site_would
2 attack - killed - taliban - syria - government 68 2_attack_killed_taliban_syria
3 gold - world - race - sport - olympic 57 3_gold_world_race_sport
4 price - bank - rate - share - company 53 4_price_bank_rate_share
5 party - vote - labour - mr - ukip 52 5_party_vote_labour_mr
6 league - season - player - premier - club 49 6_league_season_player_premier
7 cricket - england - wicket - game - test 45 7_cricket_england_wicket_game
8 crash - car - road - accident - said 42 8_crash_car_road_accident
9 wales - game - rugby - davies - hes 40 9_wales_game_rugby_davies
10 patient - health - hospital - service - ambulance 34 10_patient_health_hospital_service
11 foul - corner - half - box - kick 32 11_foul_corner_half_box
12 trump - clinton - mr - mrs - us 30 12_trump_clinton_mr_mrs
13 president - mr - africa - south - mugabe 30 13_president_mr_africa_south
14 animal - dog - bird - said - rspca 28 14_animal_dog_bird_said
15 school - education - teacher - child - pupil 26 15_school_education_teacher_child
16 world - round - number - murray - court 25 16_world_round_number_murray
17 northern - ireland - party - dup - sinn 23 17_northern_ireland_party_dup
18 album - song - like - music - band 17 18_album_song_like_music
19 fire - building - police - blaze - service 16 19_fire_building_police_blaze
20 fossil - brontosaurus - dinosaur - found - animal 16 20_fossil_brontosaurus_dinosaur_found
21 film - star - artist - novel - photograph 16 21_film_star_artist_novel
22 wage - income - living - tax - uk 11 22_wage_income_living_tax
23 gang - guerrero - prison - state - police 11 23_gang_guerrero_prison_state
24 albion - brighton - hove - burton - wigan 11 24_albion_brighton_hove_burton
25 3d - space - kelly - cmdr - flight 8 25_3d_space_kelly_cmdr

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