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
Conference NameInternational Joint Conference on Artificial Intelligence
Source PublicationProceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence
Conference Date9–15 July
Conference PlaceNew York, USA
Abstract
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.
KeywordNeural Machine Translation Rare Words
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13014
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorLi, Xiaoqing
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Li XQ,Zhang Jiajun,Zong Chengqing,et al. Towards Zero Unknown Word in Neural Machine Translation[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
Towards Zero Unknown(736KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li XQ(李小青)]'s Articles
[Zhang Jiajun]'s Articles
[Zong Chengqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li XQ(李小青)]'s Articles
[Zhang Jiajun]'s Articles
[Zong Chengqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li XQ(李小青)]'s Articles
[Zhang Jiajun]'s Articles
[Zong Chengqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Towards Zero Unknown Word in Neural Machine Translation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.