rug-compling/bimu
Bilingual Learning of Multi-sense Embeddings with Discrete Autoencoders
This project helps natural language processing researchers or developers to create word embeddings that understand multiple meanings of a word across two languages. You input parallel text in two languages (e.g., English and French) along with word alignments, and it outputs multi-sense word embedding matrices. This tool is for researchers in computational linguistics or NLP engineers working on multilingual understanding.
No commits in the last 6 months.
Use this if you need to generate high-quality, context-aware word embeddings for polysemous words in a bilingual setting to improve tasks like machine translation or cross-lingual information retrieval.
Not ideal if you only work with a single language or if you need general-purpose word embeddings that don't differentiate between word senses.
Stars
9
Forks
4
Language
Python
License
—
Category
Last pushed
Dec 01, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/rug-compling/bimu"
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...