uhh-lt/sensegram

Making sense embedding out of word embeddings using graph-based word sense induction

40
/ 100
Emerging

This project helps natural language processing practitioners clarify the different meanings of words based on how they're used in text. It takes either raw text or existing word embeddings as input and outputs distinct "sense embeddings" for each meaning of a word, like distinguishing "table (data)" from "table (furniture)". It's ideal for computational linguists, researchers, or anyone building applications that need a deeper understanding of word semantics.

213 stars. No commits in the last 6 months.

Use this if you need to differentiate the various meanings of words in your textual data to improve the precision of language understanding or semantic analysis tasks.

Not ideal if you're looking for a simple keyword extraction tool or don't require fine-grained word sense disambiguation for your application.

natural-language-processing computational-linguistics semantic-analysis text-mining information-retrieval
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

213

Forks

52

Language

Python

License

Last pushed

May 17, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/uhh-lt/sensegram"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.