A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity

Yoshinari Fujinuma, Jordan Boyd-Graber, Michael J. Paul


Abstract
Cross-lingual word embeddings encode the meaning of words from different languages into a shared low-dimensional space. An important requirement for many downstream tasks is that word similarity should be independent of language—i.e., word vectors within one language should not be more similar to each other than to words in another language. We measure this characteristic using modularity, a network measurement that measures the strength of clusters in a graph. Modularity has a moderate to strong correlation with three downstream tasks, even though modularity is based only on the structure of embeddings and does not require any external resources. We show through experiments that modularity can serve as an intrinsic validation metric to improve unsupervised cross-lingual word embeddings, particularly on distant language pairs in low-resource settings.
Anthology ID:
P19-1489
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4952–4962
Language:
URL:
https://www.aclweb.org/anthology/P19-1489
DOI:
10.18653/v1/P19-1489
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P19-1489.pdf
Video:
 https://vimeo.com/385215885