Discriminative training and maximum entropy models for statistical machine translation

被引：0
|
作者：
Och, FJ [1 ]
Ney, H [1 ]
机构：
[1] Rhein Westfal TH Aachen, Rhein Westfal TH Aachen, Dept Comp Sci, Lehrstuhl Informat 6, D-52056 Aachen, Germany
来源：
40TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE | 2002年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible hidden variables. This approach allows a baseline machine translation system to be extended easily by adding new feature functions. We show that a baseline statistical machine translation system is significantly improved using this approach.
引用
收藏
页码：295 / 302
页数：8
相关论文
共 50 条
  • [1] Maximum likelihood and discriminative training of direct translation models
    Papineni, KA
    Roukos, S
    Ward, RT
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 189 - 192
  • [2] Refined lexicon models for statistical machine translation using a maximum entropy approach
    Varea, IG
    Och, FJ
    Ney, H
    Casacuberta, F
    39TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2001, : 204 - 211
  • [3] Hope and Fear for Discriminative Training of Statistical Translation Models
    Chiang, David
    JOURNAL OF MACHINE LEARNING RESEARCH, 2012, 13 : 1159 - 1187
  • [4] A Maximum-Entropy Segmentation Model for Statistical Machine Translation
    Xiong, Deyi
    Zhang, Min
    Li, Haizhou
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (08): : 2494 - 2505
  • [5] Target-Side Context for Discriminative Models in Statistical Machine Translation
    Tamchyna, Ales
    Fraser, Alexander
    Bojar, Ondrej
    Junczys-Dowmunt, Marcin
    PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2016, : 1704 - 1714
  • [6] The Maximum Entropy based Rule Selection Model for Statistical Machine Translation
    Liu, Qun
    He, Zhongjun
    PROCEEDINGS OF THE SECOND INTERNATIONAL SYMPOSIUM ON UNIVERSAL COMMUNICATION, 2008, : 89 - 96
  • [7] Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation
    Xiong, Deyi
    Liu, Qun
    Lin, Shouxun
    COLING/ACL 2006, VOLS 1 AND 2, PROCEEDINGS OF THE CONFERENCE, 2006, : 521 - 528
  • [8] Discriminative Spoken Language Understanding Using Statistical Machine Translation Alignment Models
    Aliannejadi, Mohammad
    Khadivi, Shahram
    Ghidary, Saeed Shiry
    Bokaei, Mohammad Hadi
    ARTIFICIAL INTELLIGENCE AND SIGNAL PROCESSING, AISP 2013, 2014, 427 : 194 - +
  • [9] Maximum entropy modeling:: A suitable framework to learn context-dependent lexicon models for statistical machine translation
    García-Varea, I
    Casacuberta, F
    MACHINE LEARNING, 2005, 60 (1-3) : 135 - 158
  • [10] Efficient integration of maximum entropy lexicon models within the training of statistical alignment models
    Varea, IG
    Och, FJ
    Ney, H
    Casacuberta, F
    MACHINE TRANSLATION: FROM RESEARCH TO REAL USERS, 2002, 2499 : 54 - 63
12345