Online Large-Margin Training for Statistical Machine Translation
作者： Hideki Isozaki , Hajime Tsukada , Taro Watanabe , Jun Suzuki
DOI:
关键词: Evaluation of machine translation 、 Set (abstract data type) 、 Machine translation 、 Rule-based machine translation 、 Computer science 、 Translation (geometry) 、 Pattern recognition 、 Artificial intelligence 、 Margin (machine learning)
摘要: We achieved a state of the art performance in statistical machine translation by using large number features with an online large-margin training algorithm. The millions parameters were tuned only on small development set consisting less than 1K sentences. Experiments Arabic-toEnglish indicated that model trained sparse binary outperformed conventional SMT system features.
aclweb.org
elsevier.com参考文章(23)
Christopher D. Manning, Michael Collins, Daphne Koller, Ben Taskar, Dan Klein, Max-Margin Parsing empirical methods in natural language processing. pp. 1- 8 ,(2004)
Stephan Kanthak, Patrick Haffner, Srinivas Bangalore, Sequence classification for machine translation conference of the international speech communication association. ,(2007)
George Doddington, Automatic evaluation of machine translation quality using n-gram co-occurrence statistics international conference on human language technology research. pp. 138- 145 ,(2002) , 10.3115/1289189.1289273
Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu, BLEU Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02. pp. 311- 318 ,(2001) , 10.3115/1073083.1073135
Ryan McDonald, Koby Crammer, Fernando Pereira, Online Large-Margin Training of Dependency Parsers meeting of the association for computational linguistics. pp. 91- 98 ,(2005) , 10.3115/1219840.1219852
Nobuyuki Shimizu, Andrew Haas, Exact Decoding for Jointly Labeling and Chunking Sequences meeting of the association for computational linguistics. pp. 763- 770 ,(2006) , 10.3115/1273073.1273171
Franz Josef Och, Hermann Ney, The Alignment Template Approach to Statistical Machine Translation Computational Linguistics. ,vol. 30, pp. 417- 449 ,(2004) , 10.1162/0891201042544884
Taro Watanabe, Hajime Tsukada, Hideki Isozaki, Left-to-Right Target Generation for Hierarchical Phrase-Based Translation meeting of the association for computational linguistics. pp. 777- 784 ,(2006) , 10.3115/1220175.1220273
Percy Liang, Alexandre Bouchard-Côté, Dan Klein, Ben Taskar, An End-to-End Discriminative Approach to Machine Translation meeting of the association for computational linguistics. pp. 761- 768 ,(2006) , 10.3115/1220175.1220271
Franz Josef Och, Minimum error rate training in statistical machine translation Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03. pp. 160- 167 ,(2003) , 10.3115/1075096.1075117