Date of Original Version
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics
Copyright 2014 Association for Computational Linguistics
Abstract or Description
The distributional hypothesis of Harris (1954), according to which the meaning of words is evidenced by the contexts they occur in, has motivated several effective techniques for obtaining vector space semantic representations of words using unannotated text corpora. This paper argues that lexico-semantic content should additionally be invariant across languages and proposes a simple technique based on canonical correlation analysis (CCA) for incorporating multilingual evidence into vectors generated monolingually. We evaluate the resulting word representations on standard lexical semantic evaluation tasks and show that our method produces substantially better semantic representations than monolingual techniques.
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, 462-471.