arsena-k/discourse_atoms
How are topics encoded in semantic space? Repository to accompany PNAS article: https://www.pnas.org/doi/10.1073/pnas.2108801119
This project helps researchers and analysts uncover hidden patterns and recurring themes within large collections of text, like incident reports or survey responses. By analyzing unstructured narratives, it identifies underlying topics and shows how those topics are expressed in documents. This tool is designed for social scientists, public health researchers, and policy analysts who work with extensive qualitative data and need to extract quantitative insights.
No commits in the last 6 months.
Use this if you need to understand the latent topics within a large corpus of text and how those topics are distributed across different documents or demographic groups.
Not ideal if you're looking for a simple keyword extraction tool or don't have a large volume of text data requiring advanced statistical topic modeling.
Stars
29
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/arsena-k/discourse_atoms"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
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...