Pzoom522/xANLG

Data and code for "Understanding Linearity of Cross-Lingual Word Embedding Mappings" (TMLR 2022)

27
/ 100
Experimental

This project offers data and code to evaluate how well word meanings translate across different languages using mathematical models. It takes pre-trained word embeddings for various languages as input and checks if a simple linear transformation can accurately map words from one language to another. Researchers and computational linguists studying multilingual natural language processing (NLP) would find this useful.

No commits in the last 6 months.

Use this if you are a researcher in natural language processing and need to test the linearity of cross-lingual word embedding mappings for your linguistic analysis.

Not ideal if you are looking for a ready-to-use tool to perform cross-lingual text analysis or machine translation without a research focus.

cross-lingual NLP word embeddings computational linguistics machine translation research linguistic analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

AGPL-3.0

Last pushed

Jun 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Pzoom522/xANLG"

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