CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Addressing Troublesome Words in Neural Machine Translation
Zhao, Yang1; Zhang, Jiajun1; He, Zhongjun2; Zong, Chengqing1; Wu, Hua2
2018
会议名称EMNLP
会议日期2018-11
会议地点Brussels, Belgium
摘要

One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words. To address this problem, we propose a novel memoryenhanced NMT method. First, we investigate different strategies to define and detect the troublesome words. Then, a contextual memory is constructed to memorize which target words should be produced in what situations. Finally, we design a hybrid model to dynamically access the contextual memory so as to correctly translate the troublesome words. The extensive experiments on Chineseto-English and English-to-German translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling troublesome words.

语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23196
专题模式识别国家重点实验室_自然语言处理
作者单位1.中国科学院自动化研究所
2.百度
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zhao, Yang,Zhang, Jiajun,He, Zhongjun,et al. Addressing Troublesome Words in Neural Machine Translation[C],2018.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhao, Yang]的文章
[Zhang, Jiajun]的文章
[He, Zhongjun]的文章
百度学术
百度学术中相似的文章
[Zhao, Yang]的文章
[Zhang, Jiajun]的文章
[He, Zhongjun]的文章
必应学术
必应学术中相似的文章
[Zhao, Yang]的文章
[Zhang, Jiajun]的文章
[He, Zhongjun]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。