Towards Neural Machine Translation with Partially Aligned Corpora | |
Wang,Yining2,3; Zhao,Yang2,3; Zhang,Jiajun2,3; Zong,Chengqing2,3,4; Xue,Zhengshan1 | |
2017-11 | |
会议日期 | November 27 – December 1, 2017 |
会议地点 | Taipei, Taiwan, China |
英文摘要 | While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in which there only exists monolingual corpora and phrase pairs. We propose a new method towards translation with partially aligned sentence pairs which are derived from the phrase pairs and monolingual corpora. To make full use of the partially aligned corpora, we adapt the conventional NMT training method in two aspects. On one hand, different generation strategies are designed for aligned and unaligned target words. On the other hand, a different objective function is designed to model the partially aligned parts. The experiments demonstrate that our method can achieve a relatively good result in such a translation scenario, and tiny bitexts can boost translation quality to a large extent. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39242] ![]() |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.Toshiba (China) Co.,Ltd. 2.National Laboratory of Pattern Recognition, CASIA, Beijing, China 3.University of Chinese Academy of Sciences, Beijing, China 4.CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China |
推荐引用方式 GB/T 7714 | Wang,Yining,Zhao,Yang,Zhang,Jiajun,et al. Towards Neural Machine Translation with Partially Aligned Corpora[C]. 见:. Taipei, Taiwan, China. November 27 – December 1, 2017. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论