Explicitly Modeling Word Translations in Neural Machine Translation
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), pp. 1-17, 2020.
In this article, we show that word translations can be explicitly incorporated into NMT effectively to avoid wrong translations. Specifically, we propose three cross-lingual encoders to explicitly incorporate word translations into NMT: (1) Factored encoder, which encodes a word and its translation in a vertical way; (2) Gated encoder, wh...更多
下载 PDF 全文 (上传PDF)