BERTopic-summcomparer-gauntlet-v0p1-all-roberta-large-v1-summary

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.

document-dist

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("pszemraj/BERTopic-summcomparer-gauntlet-v0p1-all-roberta-large-v1-summary")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 25
  • Number of training documents: 1960
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 question - it - going - they - she 11 -1_question_it_going_they
0 merging - merge - operations - concept - computation 62 0_merging_merge_operations_concept
1 rainsford - island - sailors - hunted - hunting 208 1_rainsford_island_sailors_hunted
2 film - films - noir - dissertation - cinema 116 2_film_films_noir_dissertation
3 patients - predicting - predict - prediction - unsupervised 114 3_patients_predicting_predict_prediction
4 cogvideo - videos - cogview2 - cog - pretrained 108 4_cogvideo_videos_cogview2_cog
5 frozen - sled - snow - princess - hans 108 5_frozen_sled_snow_princess
6 dory - coral - fish - gill - ocean 103 6_dory_coral_fish_gill
7 captions - encoder - image - images - caption 103 7_captions_encoder_image_images
8 law - assignments - lectures - assignment - learning 99 8_law_assignments_lectures_assignment
9 convolutional - segmentation - imaging - pathology - superpixels 98 9_convolutional_segmentation_imaging_pathology
10 enhancement - enhancing - vocoding - vocoder - audio 97 10_enhancement_enhancing_vocoding_vocoder
11 tokenization - medical - health - words - embeddings 97 11_tokenization_medical_health_words
12 gillis - scene - script - sunset - movie 93 12_gillis_scene_script_sunset
13 anthony - antony - scene - guy - his 92 13_anthony_antony_scene_guy
14 topic - projects - sociology - research - students 90 14_topic_projects_sociology_research
15 peter - conversation - asks - questions - cheesy 88 15_peter_conversation_asks_questions
16 sniper - marine - unarmed - combat - trained 86 16_sniper_marine_unarmed_combat
17 communication - apparatus - method - input - embodiment 68 17_communication_apparatus_method_input
18 words - phrases - political - unsupervised - topic 27 18_words_phrases_political_unsupervised
19 clustering - similarity - unsupervised - topic - plagiarism 23 19_clustering_similarity_unsupervised_topic
20 book - novel - father - read - arrives 21 20_book_novel_father_read
21 topic - loans - clustering - loan - analyze 19 21_topic_loans_clustering_loan
22 sciences - science - society - research - scientists 16 22_sciences_science_society_research
23 dynamics - situation - quantum - mechanics - note 13 23_dynamics_situation_quantum_mechanics

hierarchy

hierarchy

Training hyperparameters

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

Framework versions

  • Numpy: 1.22.4
  • HDBSCAN: 0.8.29
  • UMAP: 0.5.3
  • Pandas: 1.5.3
  • Scikit-Learn: 1.2.2
  • Sentence-transformers: 2.2.2
  • Transformers: 4.29.2
  • Numba: 0.56.4
  • Plotly: 5.13.1
  • Python: 3.10.11
Downloads last month
18
Inference Examples
Inference API (serverless) has been turned off for this model.

Dataset used to train pszemraj/BERTopic-summcomparer-gauntlet-v0p1-all-roberta-large-v1-summary