Recently neural machine translation(NMT)has achieved remarkable success in sentence-level translation.However,it still cannot resolve a wide variety of discourse phenomena,such as lexical cohesion and coreference,which can be alleviated by using context information in document-level translation.In contrast to existing studies of modeling source-side context,this paper proposes to model target-side context in document-level NMT.Specifically,motivated by deliberation networks,our approach translates source-side document twice.In the first-pass transla-tion,it performs sentence-level translation.In the second-pass,it properly translates each sentence by modeling the target-side context which has just be generated from the first-pass translation.Experimental results on LDC Chinese-to-English and WMT English-to-German document-level translation tasks show that our approach significantly im-proves translation performance by introducing few parameters.Meanwhile,it is observed that the proposed approach benefits more if the performance of the first-pass translation(i.e.,sentence-level NMT)is improved.
NETL
NSTL
万方数据
