Automatic Long Sentence Segmentation for Neural Machine Translation

摘要：

　　Neural machine translation(NMT)is an emerging machine translation paradigm that translates texts with an encoder-decoder neural architecture.Very recent studies find that translation quality drops significantly when NMT translates long sentences.In this paper,we propose a novel method to deal with this issue by segmenting long sentences into several clauses.We introduce a split and reordering model to collectively detect the optimal sequence of segmentation points for a long source sentence.Each segmented clause is translated by the NMT system independently into a target clause.The translated target clauses are then concatenated without reordering to form the final translation for the long sentence.On NIST Chinese-English translation tasks,our segmentation method achieves a substantial improvement of 2.94 BLEU points over the NMT baseline on translating long sentences with more than 30 words,and 5.43 BLEU points on sentences of over 40 words.

作者: Shaohui Kuang Deyi Xiong

作者单位: Soochow University,Suzhou,China

会议类型: 国际会议

会议名称: 第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)

会议地点: 昆明

会议语种:英文

页码: 1-12

在线出版日期: 2016-12-02（万方平台首次上网日期，不代表论文的发表时间）