|
--- |
|
tags: |
|
- bertopic |
|
library_name: bertopic |
|
pipeline_tag: text-classification |
|
inference: false |
|
license: apache-2.0 |
|
datasets: |
|
- pszemraj/summcomparer-gauntlet-v0p1 |
|
language: |
|
- en |
|
--- |
|
|
|
# BERTopic-summcomparer-gauntlet-v0p1-sentence-t5-xl-summary |
|
|
|
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model. |
|
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets. |
|
|
|
|
|
Hierarchy of topics: |
|
|
|
 |
|
|
|
## Usage |
|
|
|
To use this model, please install BERTopic: |
|
|
|
``` |
|
pip install -U -q bertopic safetensors |
|
``` |
|
|
|
You can use the model as follows: |
|
|
|
```python |
|
from bertopic import BERTopic |
|
topic_model = BERTopic.load("pszemraj/BERTopic-summcomparer-gauntlet-v0p1-sentence-t5-xl-summary") |
|
|
|
topic_model.visualize_topics() |
|
|
|
# for dataframe: |
|
# topic_model.get_topic_info() |
|
``` |
|
|
|
predicting new instances: |
|
|
|
```python |
|
topic, embedding = topic_model.transform(text) |
|
print(topic) |
|
``` |
|
|
|
|
|
## Topic overview |
|
|
|
* Number of topics: 24 |
|
* Number of training documents: 1960 |
|
|
|
<details> |
|
<summary>Click here for an overview of all topics.</summary> |
|
|
|
| Topic ID | Topic Keywords | Topic Frequency | Label | |
|
|----------|----------------|-----------------|-------| |
|
| -1 | no_saic_raw_sp - sep_4 - sec - data - image | 13 | -1_no_saic_raw_sp_sep_4_sec_data | |
|
| 0 | lecture - applications - methods - learning - topics | 104 | 0_lecture_applications_methods_learning | |
|
| 1 | cogvideo - videos - cogview2 - cog - video | 303 | 1_cogvideo_videos_cogview2_cog | |
|
| 2 | ship - rainsford - hunted - island - hunts | 117 | 2_ship_rainsford_hunted_island | |
|
| 3 | films - dissertation - film - noir - identity | 106 | 3_films_dissertation_film_noir | |
|
| 4 | linguistics - language - languages - foundational - systems | 104 | 4_linguistics_language_languages_foundational | |
|
| 5 | nemo - dory - transcript - clownfish - fish | 103 | 5_nemo_dory_transcript_clownfish | |
|
| 6 | train - bruno - washington - station - tennis | 102 | 6_train_bruno_washington_station | |
|
| 7 | images - representations - image - captions - representation | 102 | 7_images_representations_image_captions | |
|
| 8 | merge - merging - explain - concept - problems | 102 | 8_merge_merging_explain_concept | |
|
| 9 | enhancement - enhancing - recordings - improve - waveforms | 100 | 9_enhancement_enhancing_recordings_improve | |
|
| 10 | arendelle - elsa - frozen - kristoff - olaf | 99 | 10_arendelle_elsa_frozen_kristoff | |
|
| 11 | scene - story - script - movie - gillis | 97 | 11_scene_story_script_movie | |
|
| 12 | lecture - lemmatization - nlp - medical - techniques | 96 | 12_lecture_lemmatization_nlp_medical | |
|
| 13 | questions - topics - conversation - terrance - talk | 85 | 13_questions_topics_conversation_terrance | |
|
| 14 | sniper - kill - fury - combat - narrator | 81 | 14_sniper_kill_fury_combat | |
|
| 15 | images - lecture - ezurich - pathology - medical | 67 | 15_images_lecture_ezurich_pathology | |
|
| 16 | timeseries - framework - interpretability - representations - next_concept | 37 | 16_timeseries_framework_interpretability_representations | |
|
| 17 | prediction - predictions - forecasting - predict - markov | 27 | 17_prediction_predictions_forecasting_predict | |
|
| 18 | images - imaging - computational - convolutional - lecture | 27 | 18_images_imaging_computational_convolutional | |
|
| 19 | technology - treatment - methods - medical - detection | 27 | 19_technology_treatment_methods_medical | |
|
| 20 | novel - translation - henry - read - learn | 23 | 20_novel_translation_henry_read | |
|
| 21 | abridged - brief - synopsis - short - citations | 22 | 21_abridged_brief_synopsis_short | |
|
| 22 | lecture - pathology - medical - computational - patients | 16 | 22_lecture_pathology_medical_computational | |
|
|
|
</details> |
|
|
|
## 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 |
