y3ro/meemi
Improving cross-lingual word embeddings by meeting in the middle
This project provides pre-trained word embeddings that improve the understanding of relationships between words across different languages like English, Spanish, German, Italian, and Finnish. It takes existing word embeddings (lists of words with numerical representations) and a dictionary of equivalent words in two languages, then outputs enhanced cross-lingual word embeddings. This is useful for researchers and practitioners working on natural language processing tasks who need to work with text data in multiple languages.
No commits in the last 6 months.
Use this if you need to perform natural language processing tasks that require understanding word meanings and relationships across different languages, such as comparing document similarity or finding related terms.
Not ideal if your work only involves a single language or if you need to work with languages not covered by the provided pre-trained models.
Stars
23
Forks
4
Language
Python
License
GPL-3.0
Category
Last pushed
Aug 25, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/y3ro/meemi"
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...