BERTopic-summcomparer-gauntlet-v0p1-sentence-t5-xl-document_text

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("pszemraj/BERTopic-summcomparer-gauntlet-v0p1-sentence-t5-xl-document_text")

topic_model.get_topic_info()

Topic overview

• Number of topics: 16
• Number of training documents: 630

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	convolutional - images - networks - superpixels - overfitting	12	-1_convolutional_images_networks_superpixels
0	bruno - guy - pdf - screentalk - he	26	0_bruno_guy_pdf_screentalk
1	elsa - arendelle - kristoff - frozen - anna	94	1_elsa_arendelle_kristoff_frozen
2	gillis - script - room - ll - artie	73	2_gillis_script_room_ll
3	interpretation - explanation - theory - structure - merge	72	3_interpretation_explanation_theory_structure
4	topics - topic - documents - corpus - document	63	4_topics_topic_documents_corpus
5	nemo - dory - chum - gill - fish	56	5_nemo_dory_chum_gill
6	films - film - identity - trauma - zinnemann	54	6_films_film_identity_trauma
7	computational - data - pathology - medical - informatics	47	7_computational_data_pathology_medical
8	images - captions - representations - embeddings - image	26	8_images_captions_representations_embeddings
9	zaroff - rainsford - hunt - hunting - general	24	9_zaroff_rainsford_hunt_hunting
10	cogvideo - interpolation - videos - coglm - frames	24	10_cogvideo_interpolation_videos_coglm
11	assignment - essays - questions - projects - students	17	11_assignment_essays_questions_projects
12	things - ll - some - lol - explain	16	12_things_ll_some_lol
13	videos - arxiv - visual - preprint - generative	13	13_videos_arxiv_visual_preprint
14	spectrograms - musecoder - melspectrogram - vocoding - spectrogram	13	14_spectrograms_musecoder_melspectrogram_vocoding

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