English

Cross-lingual Models of Word Embeddings: An Empirical Comparison

Computation and Language 2016-06-09 v2

Abstract

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.

Keywords

Cite

@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}
}

Comments

To appear at ACL 2016