Learning bilingualword embeddings using lexical definitions

Abstract

Bilingual word embeddings, which represent lexicons of different languages in a shared embedding space, are essential for supporting semantic and knowledge transfers in a variety of cross-lingual NLP tasks. Existing approaches to training bilingual word embeddings require often require pre-defined seed lexicons that are expensive to obtain, or parallel sentences that comprise coarse and noisy alignment. In contrast, we propose BilLex that leverages publicly available lexical definitions for bilingual word embedding learning. Without the need of predefined seed lexicons, BilLex comprises a novel word pairing strategy to automatically identify and propagate the precise finegrained word alignment from lexical definitions. We evaluate BilLex in word-level and sentence-level translation tasks, which seek to find the cross-lingual counterparts of words and sentences respectively. BilLex significantly outperforms previous embedding methods on both tasks.