Massively Multilingual Word Embeddings
Computation and Language
2016-05-24 v2
Abstract
We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Our estimation methods, multiCluster and multiCCA, use dictionaries and monolingual data; they do not require parallel data. Our new evaluation method, multiQVEC-CCA, is shown to correlate better than previous ones with two downstream tasks (text categorization and parsing). We also describe a web portal for evaluation that will facilitate further research in this area, along with open-source releases of all our methods.
Cite
@article{arxiv.1602.01925,
title = {Massively Multilingual Word Embeddings},
author = {Waleed Ammar and George Mulcaire and Yulia Tsvetkov and Guillaume Lample and Chris Dyer and Noah A. Smith},
journal= {arXiv preprint arXiv:1602.01925},
year = {2016}
}