? 在神经机器翻译中优化不可分解的评价指标
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (4) :796-804    DOI: 10.1007/s11390-017-1760-9
Special Issue on Deep Learning << Previous Articles | Next Articles >>
在神经机器翻译中优化不可分解的评价指标
Shi-Qi Shen1,2,3, Student Member, CCF, Yang Liu1,2,3,4,*, Senior Member, CCF, Mao-Song Sun1,2,3,4, Senior Member, CCF
1 Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China;
2 State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China;
3 Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing 100084, China;
4 Jiangsu Collaborative Innovation Center for Language Ability, Jiangsu Normal University, Xuzhou 221009, China
Optimizing Non-Decomposable Evaluation Metrics for Neural Machine Translation
Shi-Qi Shen1,2,3, Student Member, CCF, Yang Liu1,2,3,4,*, Senior Member, CCF, Mao-Song Sun1,2,3,4, Senior Member, CCF
1 Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China;
2 State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China;
3 Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing 100084, China;
4 Jiangsu Collaborative Innovation Center for Language Ability, Jiangsu Normal University, Xuzhou 221009, China

摘要
参考文献
相关文章
Download: [PDF 311KB]  
摘要 尽管针对评价指标来优化模型参数被验证是对端到端的神经机器翻译有利的,但由于在训练中需要使用在线学习算法,因此研究者们使用的评价指标往往被限制为句子级别。而这并不是研究者们的初衷,因为在测试阶段最终的评价指标一般是不可分解的(即,语料库级别的评价指标不可以由句子级别的值加和得到)。为了减小训练和测试阶段的不一致性,我们提出扩展最小风险训练算法,将不可分解的语料库级别的评价指标纳入考虑,同时仍然保持在线学习的优势。我们在在线学习算法中使用训练数据的一个子集来近似计算语料库级别的评价指标。中文-英文和英文-法文翻译任务上的实验证明我们的方法能够提高训练和测试阶段的一致性,相比于使用可分解评价指标的最小风险训练算法,我们的方法取得了显著的提升。
关键词神经机器翻译   训练准则   不可分解评价指标     
Abstract: While optimizing model parameters with respect to evaluation metrics has recently proven to benefit endto-end neural machine translation (NMT), the evaluation metrics used in the training are restricted to be defined at the sentence level to facilitate online learning algorithms. This is undesirable because the final evaluation metrics used in the testing phase are usually non-decomposable (i.e., they are defined at the corpus level and cannot be expressed as the sum of sentence-level metrics). To minimize the discrepancy between the training and the testing, we propose to extend the minimum risk training (MRT) algorithm to take non-decomposable corpus-level evaluation metrics into consideration while still keeping the advantages of online training. This can be done by calculating corpus-level evaluation metrics on a subset of training data at each step in online training. Experiments on Chinese-English and English-French translation show that our approach improves the correlation between training and testing and significantly outperforms the MRT algorithm using decomposable evaluation metrics.
Keywordsneural machine translation   training criterion   non-decomposable evaluation metric     
Received 2016-12-20;
本文基金:

This work is supported by the National Natural Science Foundation of China under Grant Nos. 61522204, 61432013, and the National High Technology Research and Development 863 Program of China under Grant No. 2015AA015407, also supported by the Singapore National Research Foundation under Its International Research Centre@Singapore Funding Initiative, and administered by the IDM (Interactive Digital Media) Programme.

通讯作者: Yang Liu     Email: liuyang2011@tsinghua.edu.cn
About author: Shi-Qi Shen is currently working toward his Ph.D. degree in computer science at Tsinghua University, Beijing. His current research interests include natural language processing and machine translation.
引用本文:   
Shi-Qi Shen, Yang Liu, Mao-Song.在神经机器翻译中优化不可分解的评价指标[J]  Journal of Computer Science and Technology , 2017,V32(4): 796-804
Shi-Qi Shen, Yang Liu, Mao-Song.Optimizing Non-Decomposable Evaluation Metrics for Neural Machine Translation[J]  Journal of Computer Science and Technology, 2017,V32(4): 796-804
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1760-9
Copyright 2010 by Journal of Computer Science and Technology