MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).
This project helps researchers and analysts discover hidden themes within large collections of text documents, such as articles, reviews, or social media posts. By taking your raw text data, it outputs coherent topics that summarize the content, even across multiple languages. It's designed for anyone working with unstructured text who needs to understand the main subjects being discussed without manually reading every document.
1,266 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to automatically identify the main subjects or themes across a large body of text documents, especially if those documents are in different languages or contain specialized vocabulary that traditional keyword methods struggle with.
Not ideal if your primary goal is to classify documents into pre-defined categories with high precision, or if you only have a very small number of documents to analyze.
Stars
1,266
Forks
150
Language
Python
License
MIT
Category
Last pushed
Jul 24, 2025
Commits (30d)
0
Dependencies
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/MilaNLProc/contextualized-topic-models"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...
ina-foss/twembeddings
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and...