pabvald/semantic-similarity

Comparison of methods based on pre-trained Word2Vec, GloVe and FastText vectors to measure the semantic similarity between sentence pairs

28
/ 100
Experimental

This project helps developers and researchers evaluate and compare different techniques for determining how similar the meaning is between pairs of sentences. It takes pre-trained word embedding models (like Word2Vec, GloVe, and FastText) and a dataset of sentence pairs, then outputs a quantitative comparison of how well each method measures semantic similarity. This is for anyone building or evaluating natural language processing systems where understanding sentence meaning is crucial.

No commits in the last 6 months.

Use this if you are a machine learning engineer or NLP researcher comparing state-of-the-art methods for sentence semantic similarity.

Not ideal if you need an out-of-the-box solution for applying semantic similarity to your own data or building a production application.

natural-language-processing semantic-analysis text-comparison machine-learning-evaluation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Jupyter Notebook

License

AGPL-3.0

Last pushed

Mar 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/pabvald/semantic-similarity"

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