Discriminative Latent Variable Based Classifier for Translation Error Detection

摘要：

　　This paper presents a discriminative latent variable model (DPLVM) based classifier for improving the translation error detection performance for statistical machine translation (SMT).It uses latent variables to carry additional information which may not be expressed by those original labels and capture more complicated dependencies be tween translation errors and their corresponding features to improve the classification performance.Specifically, we firstly detail the mathemati cal representation of the proposed DPLVM method, and then introduce features, namely word posterior probabilities (WPP), linguistic features, syntactic features.Finally, we compare the proposed method with Max Ent and SVM classifiers to verify its effectiveness.Experimental results show that the proposed DPLVM-based classifier reduce classification er ror rate (CER) by relative 1.75%, 1.69%, 2.61% compared to the MaxEnt classifier, and relative 0.17%, 0.91%, 2.12% compared to the SVM clas sifter over three different feature combinations.

关键词： Translation Error Detection Binary Classification MaxEnt Classifier SVM Classifier DPLVM Classifier

作者: Jinhua Du Junbo Guo Fei Zhao

作者单位: Faculty of Automation and Information Engineering Faculty of High Vocational Education, Xian University of Technology, Xian, 710048 China

会议类型: 国际会议

会议名称: Second CCF Conference,NLPCC2013(第二届自然语言处理与中文计算会议)

会议地点: 重庆

会议语种:英文

页码: 127-138

在线出版日期: 2013-11-15（万方平台首次上网日期，不代表论文的发表时间）