CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Towards Zero Unknown Word in Neural Machine Translation
Li XQ(李小青); Zhang Jiajun; Zong Chengqing; Li, Xiaoqing
2016
会议名称International Joint Conference on Artificial Intelligence
会议录名称Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence
会议日期9–15 July
会议地点New York, USA
摘要
Neural Machine translation has shown promising results in recent years. In order to control the computational complexity, NMT has to employ a small vocabulary, and massive rare words outside the vocabulary are all replaced with a single unk symbol. Besides the inability to translate rare words, this kind of simple approach leads to much increased ambiguity of the sentences since meaningless unks break the structure of sentences, and thus hurts the translation and reordering of the in-vocabulary words. To tackle this roblem, we propose a novel substitution-translation-restoration method. In substitution step, the rare words in a testing sentence are replaced with similar in-vocabulary words based on a similarity model learnt from monolingual data. In translation and restoration steps, the sentence will be translated with a model trained on new bilingual data with rare words replaced, and finally the translations of the replaced words will be substituted by that of original ones. Experiments on Chinese-to-English translation demonstrate that our proposed method can achieve more than 4 BLEU points over the attention-based NMT. When compared to the recently proposed method handling rare words in NMT, our method can also obtain an improvement by nearly 3 BLEU points.
关键词Neural Machine Translation Rare Words
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/13014
专题模式识别国家重点实验室_自然语言处理
通讯作者Li, Xiaoqing
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Li XQ,Zhang Jiajun,Zong Chengqing,et al. Towards Zero Unknown Word in Neural Machine Translation[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Towards Zero Unknown(736KB)会议论文 开放获取CC BY-NC-SA浏览 下载
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
[Li XQ(李小青)]的文章
[Zhang Jiajun]的文章
[Zong Chengqing]的文章
百度学术
百度学术中相似的文章
[Li XQ(李小青)]的文章
[Zhang Jiajun]的文章
[Zong Chengqing]的文章
必应学术
必应学术中相似的文章
[Li XQ(李小青)]的文章
[Zhang Jiajun]的文章
[Zong Chengqing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Towards Zero Unknown Word in Neural Machine Translation.pdf
格式: Adobe PDF
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。