Synchronous Bidirectional Neural Machine Translation

Long ZhouJiajun ZhangChengqing Zong

   Papers with code   Abstract  PDF

Existing approaches to neural machine translation (NMT) generate the target language sequence token by token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the target-side future contexts which can be produced in a right-to-left decoding direction, and thus suffers from the issue of unbalanced outputs... (read more)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.