Bilingual Learning of Multi-sense Embeddings with Discrete Autoencoders
This work addresses the challenge of improving word sense disambiguation and representation for natural language processing applications, though it appears incremental by combining existing bilingual and monolingual approaches.
The paper tackled the problem of learning multi-sense word embeddings by using both monolingual and bilingual information, resulting in bilingual-induced representations outperforming monolingual ones across various evaluation tasks.
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.