CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
A Class-specific Copy Network for Handling the Rare Word Problem in Neural Machine Translation
Feng Wang; Wei Chen; Zhen yang; Xiaowei Zhang; Shuang Xu; Bo Xu
2017
Conference NameInternational Joint Conference on Neural Networks
Source PublicationIJCNN
Pages2658-2664
Conference Date14-19 May 2017
Conference PlaceAnchorage, AK, USA
AbstractNeural machine translation (NMT) has shown promising results and rapidly gained adoption in many large-scale settings. With the NMT model being widely used in empirical productions, its long-standing weakness in handling the rare and out of vocabulary words has been amplified a lot. In order to release the model from the stress of “understanding” the rare words, copy mechanism has been proposed to deal with the rare and unseen words for the neural network models using attention. However the negative side of the copy mechanism is that the model is only able to decide whether to copy or not. It is unable to detect which class should the rare word be copied to, such as person, location, and organization. This paper deeply investigates this limitation of the NMT model. As a result, we propose a new NMT model by novelly incorporating a class-specific copy network. With the network, the proposed NMT model is able to decide which class the words in the target belong to and which class in the source should be copied to. Experimental results on Chinese-English translation tasks show that the proposed model outperforms the traditional NMT model with a large margin especially for sentences containing the rare words.
KeywordNeural Machine Translation (Nmt) Copy Network Rare Word
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15428
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Corresponding AuthorWei Chen
AffiliationInstitute of Automation Chinese Academy of Science
Recommended Citation
GB/T 7714
Feng Wang,Wei Chen,Zhen yang,et al. A Class-specific Copy Network for Handling the Rare Word Problem in Neural Machine Translation[C],2017:2658-2664.
Files in This Item: Download All
File Name/Size DocType Version Access License
07966181.pdf(361KB)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
[Feng Wang]'s Articles
[Wei Chen]'s Articles
[Zhen yang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Feng Wang]'s Articles
[Wei Chen]'s Articles
[Zhen yang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Feng Wang]'s Articles
[Wei Chen]'s Articles
[Zhen yang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 07966181.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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