English

Learning Bilingual Word Embeddings Using Lexical Definitions

Computation and Language 2020-01-07 v1 Artificial Intelligence Machine Learning

Abstract

Bilingual word embeddings, which representlexicons of different languages in a shared em-bedding space, are essential for supporting se-mantic and knowledge transfers in a variety ofcross-lingual NLP tasks. Existing approachesto training bilingual word embeddings requireoften require pre-defined seed lexicons that areexpensive to obtain, or parallel sentences thatcomprise coarse and noisy alignment. In con-trast, we propose BilLex that leverages pub-licly available lexical definitions for bilingualword embedding learning. Without the needof predefined seed lexicons, BilLex comprisesa novel word pairing strategy to automati-cally identify and propagate the precise fine-grained word alignment from lexical defini-tions. We evaluate BilLex in word-level andsentence-level translation tasks, which seek tofind the cross-lingual counterparts of wordsand sentences respectively.BilLex signifi-cantly outperforms previous embedding meth-ods on both tasks.

Keywords

Cite

@article{arxiv.1906.08939,
  title  = {Learning Bilingual Word Embeddings Using Lexical Definitions},
  author = {Weijia Shi and Muhao Chen and Yingtao Tian and Kai-Wei Chang},
  journal= {arXiv preprint arXiv:1906.08939},
  year   = {2020}
}

Comments

ACL 2019 RepL4NLP

R2 v1 2026-06-23T09:59:35.665Z