Syntactic phrase-based statistical machine translation

被引:3
|
作者
Hassan, Hany [1 ]
Heame, Mary [1 ]
Way, Andy [1 ]
Sima'an, Khalil [2 ]
机构
[1] Dublin City Univ, Sch Comp, Dublin 9, Ireland
[2] Univ Amsterdam, ILLC, NL-1018 TV Amsterdam, Netherlands
基金
爱尔兰科学基金会;
关键词
D O I
10.1109/SLT.2006.326799
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Phrase-based Statistical Machine Translation (PBSMT) systems represent the dominant approach in MT today. However, unlike systems in other paradigms, it has proven difficult to date to incorporate syntactic knowledge in order to improve translation quality. This paper improves on recent research which uses 'syntactified' target language phrases, by incorporating supertags as constraints to better resolve parse tree fragments. In addition, we do not impose any sentence-length limit, and using a log-linear decoder, we outperform a state-of-the-art PBSMT system by over 1.3 BLEU points (or 15 1 % relative) on the NIST 2003 Arabic-English test corpus.
引用
收藏
页码:238 / +
页数:3
相关论文
共 50 条
  • [41] Phrase-Based Machine Translation based on Simulated Annealing
    Lavecchia, Caroline
    Langlois, David
    Smaili, Kamel
    SIXTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, LREC 2008, 2008, : 3123 - 3129
  • [42] Using collocation segmentation to extract translation units in a phrase-based statistical machine translation system
    Costa-jussa, Marta R.
    Daudaravicius, Vidas
    Banchs, Rafael E.
    PROCESAMIENTO DEL LENGUAJE NATURAL, 2010, (45): : 215 - 220
  • [43] BETTER STATISTICAL ESTIMATION CAN BENEFIT ALL PHRASES IN PHRASE-BASED STATISTICAL MACHINE TRANSLATION
    Sima'an, Khalil
    Mylonakis, Markos
    2008 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY: SLT 2008, PROCEEDINGS, 2008, : 237 - 240
  • [44] The CASIA phrase-based machine translation system
    Yang, ZD
    Chen, ZB
    Pang, W
    Wei, W
    Xu, B
    PROCEEDINGS OF THE 2005 IEEE INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING AND KNOWLEDGE ENGINEERING (IEEE NLP-KE'05), 2005, : 416 - 419
  • [45] Phrase-based statistical machine translation by using reordering search and additional features
    Li, Miao
    Gao, Peng
    Zhang, Jian
    Luo, Yi
    COMPUTATIONAL INTELLIGENCE, PT 2, PROCEEDINGS, 2006, 4114 : 510 - 517
  • [46] Comparing and integrating alignment template and standard phrase-based statistical machine translation
    Xu, Lin
    Cao, Xiaoguang
    Zhang, Bufeng
    Li, Mu
    Computational Linguistics and Intelligent Text Processing, 2007, 4394 : 420 - 431
  • [47] A Hybrid Phrase-based/Statistical Speech Translation System
    Stallard, David
    Choi, Fred
    Krstovski, Kriste
    Natarajan, Prem
    Prasad, Rohit
    Saleem, Shirin
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 757 - 760
  • [48] Integrating Rules and Dictionaries from Shallow-Transfer Machine Translation into Phrase-Based Statistical Machine Translation
    Sanchez-Cartagena, Victor M.
    Antonio Perez-Ortiz, Juan
    Sanchez-Martinez, Felipe
    JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2016, 55 : 17 - 61
  • [49] Integrating Source-Side Semantic Roles into a Phrase-Based Statistical Machine Translation
    Zavareh, Mahnaz Namazi
    Khadivi, Shahram
    2017 25TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2017, : 2140 - 2146
  • [50] Czech-English phrase-based machine translation
    Bojar, Ondrej
    Matusov, Evgeny
    Ney, Hermann
    Lect. Notes Comput. Sci., (214-224):