Despite interest in using cross-lingual knowledge to learn word embeddings for various tasks, a systematic comparison of the possible approaches is lacking in the literature. We perform an extensive evaluation of four popular approaches of inducing cross-lingual embeddings, each requiring a different form of supervision, on four typographically different language pairs. Our evaluation setup spans four different tasks, including intrinsic evaluation on mono-lingual and cross-lingual similarity, and extrinsic evaluation on downstream semantic and syntactic applications. We show that models which require expensive cross-lingual knowledge almost always perform better, but cheaply supervised models often prove competitive on certain tasks.
@article{arxiv.1604.00425,
title = {Cross-lingual Models of Word Embeddings: An Empirical Comparison},
author = {Shyam Upadhyay and Manaal Faruqui and Chris Dyer and Dan Roth},
journal= {arXiv preprint arXiv:1604.00425},
year = {2016}
}