Bilingual Word Embeddings for Phrase-Based Machine Translation

Abstract

We introduce bilingual word embeddings: se-mantic embeddings associated across two lan-guages in the context of neural language mod-els. We propose a method to learn bilingual embeddings from a large unlabeled corpus, while utilizing MT word alignments to con-strain translational equivalence. The new em-beddings significantly out-perform baselines in word semantic similarity. A single semantic similarity feature induced with bilingual em-beddings adds near half a BLEU point to the results of NIST08 Chinese-English machine translation task. 1