Source Segment Encoding for Neural Machine Translation

摘要：

　　Sequential word encoding lacks explicit representations of structural dependencies(e.g.tree,segment)over the source words in neural machine translation.Instead of using source syntax,in this paper we propose a source segment encoding(SSE)approach to modeling source segments in encoding process by two methods.One is to encode offthe-shelf n-grams of the source sentence into original source memory.The other is to jointly learn an optimal segmentation model with the translation model in an end-to-end manner without any supervision of segmentation.Experimental results show that the SSE method yields an improvement of 2.1+BLEU points over the baselines on the Chinese-English translation task.

关键词： Source segment encoding Structure learning Neural machine translation

作者: Qiang Wang Tong Xiao Jingbo Zhu

作者单位: Natural Language Processing Lab,Northeastern University,Shenyang,China;NiuTrans Inc.,Shenyang,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 329-340

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）