作者
Simon Šuster, Ivan Titov, Gertjan van Noord
发表日期
2016/3/30
期刊
NAACL
简介
We present an approach to learning multi-sense word embeddings relying both on monolingual and bilingual information. Our model consists of an encoder, which uses monolingual and bilingual context (i.e. a parallel sentence) to choose a sense for a given word, and a decoder which predicts context words based on the chosen sense. The two components are estimated jointly. We observe that the word representations induced from bilingual data outperform the monolingual counterparts across a range of evaluation tasks, even though crosslingual information is not available at test time.
学术搜索中的文章
S Šuster, I Titov, G Van Noord - arXiv preprint arXiv:1603.09128, 2016