Discriminative Latent Model Based Chinese Multiword Expression Extraction

作     者：Xiao, Sun Sun Xiao AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine,Hefei University of Technology,Hefei 230009,P.R.China School of Computer Science and Technology,Dalian University of Technology,Dalian 116024,P.R.China

作者机构：Hefei Univ Technol AnHui Prov Key Lab Affect Comp & Adv Intelligent Hefei 230009 Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian 116024 Peoples R China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2012年第9卷第3期

页      面：124-133页

核心收录：

学科分类：0810[工学-信息与通信工程] 081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 081001[工学-通信与信息系统] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by Liaoning Province Doctor Startup Fund under Grant No.20101021 the Fund of the State Ethic Affairs Commissions under Grant No.10DL08 AnHui Provincie Key Laboratory of Affective Computing and Advanced Intelligent Machine 

主　　题：informationguage processing MT sions processing natural lan-DLM multiword expres- 

摘      要：Discriminative Latent Model(DLM) is proposed for Multiword Expressions(MWEs) extraction in Chinese text to improve the performance of Machine Translation(MT) system such as Template Based MT(TBMT).For MT systems to become of further practical use,they need to be enhanced with MWEs processing *** our study towards this goal,we propose DLM,which is developed for sequence labeling task including hidden structures,to extract MWEs for MT *** combines the advantages of existing discriminative models,which can learn hidden structures in sequence labeling *** our evaluations,DLM achieves precisions ranging up to 90.73% for some type of MWEs,which is higher than state-of-the-art discriminative *** results demonstrate that it is feasible to automatically identify many Chinese MWEs using our DLM *** MWEs processing model,BLEU score of MT system has also been increased by up to 0.3 in close test.