tca19/dict2vec

Dict2vec is a framework to learn word embeddings using lexical dictionaries.

46
/ 100
Emerging

Combines Wikipedia corpora with dictionary definition pairs (strong and weak semantic relationships) during training to improve embedding quality. The C-based implementation supports multi-threaded training and includes comprehensive evaluation against 13 word similarity benchmarks with Spearman correlation scoring. Provides pre-trained embeddings (100-300 dimensions) and utilities to fetch definitions from online dictionaries and generate training pairs automatically.

115 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

115

Forks

29

Language

Python

License

GPL-3.0

Last pushed

Jan 08, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/tca19/dict2vec"

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