词对齐是统计机器翻译中的重要技术之一。该文提出了一种重对齐方法,它在IBM models获得的正反双向词对齐的基础上,确定出正反双向对齐不一致的部分。之后,对双向词对齐不一致的部分进行重新对齐以得到更好的对称化的词对齐结果。此外,该文提出的方法还可以利用大规模单语语料来强化对齐结果。实验结果表明,相比在统计机器翻译中广泛使用的基于启发信息的词对齐对称化方法,该文提出的方法可以使统计机器翻译系统得到更高的翻译准确率。
Abstract
Word alignment is one of the key techniques in statistical machine translation (SMT). In this paper, we propose a word realignment method, which recognizes the inconsistent parts between the bidirectional alignments generated by IBM models at first, and refines then the word alignment by realigning the inconsistent parts. To reinforce our method, a monolingual feature is used to make benefits from large-scale monolingual corpus. The effectiveness of the method is demonstrated on a state-of-the-art phrase-based SMT system. The experimental results show that our method can achieve higher translation accuracy than the widely-adopted heuristics-based method.
Key wordsartificial intelligence; machine translation; statistical machine translation; word alignment; word realignment; IBM models
关键词
人工智能 /
机器翻译 /
统计机器翻译 /
词对齐 /
重对齐 /
IBM models
{{custom_keyword}} /
Key words
artificial intelligence /
machine translation /
statistical machine translation /
word alignment /
word realignment /
IBM models
/
/
/
/
/
/
/
/
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Philipp Koehn, Franz Josef Och ,and Daniel Marcu. Statistical Phrase-Based Translation [C]//Proc. of HLT/NAACL2003. 2003: 48-54.
[2] Franz Josef Och and Hermann Ney. A systematic comparison of various statistical alignment models [J]. Computational Linguistics, 2003, 29(1):19-51.
[3] Alexander Fraer and Daniel Marcu. Measuring word alignment quality for statistical machine translation [R]. Technical Report ISI-TR-616. ISI/University of Southern California, 2006.
[4] Peter F. Brown, Stephen A. Della Piatra, Vincent J. Della Pietra, and R. L. Mercer. The mathematics of statistical machine translation: Parameter estimation [J]. Computational Linguistics. 1993, 19(2):263-311.
[5] Percy Liang, Ben Taskar, and Dan Klein. Alignment by agreement [C]//Proc. of HLT/NAACL2006. 2006: 104-111.
[6] Yang Liu, Qun Liu, and Shouxin Lin. Log-linear models for word alignment [C]//Proc. of ACL2005. 2005: 459-466.
[7] Alexander Fraer and Daniel Marcu. Semi-Supervised Training for Statistical Word Alignment [C]//Proc. of ACL2006. 2006: 769-776.
[8] Abraham Ittycheriah and Salim Roukos. A maximum entropoy word aligner for Arabic-English machine translation [C]//Proc. of HLT/EMNLP2005. 2005: 89-96.
[9] Ben Taskar, Simon Lacoste-Julien, and Dan Klein. A discriminative matching approach to word alignment [C]//Proc. of HLT/EMNLP2005. 2005: 73-80.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金资助项目(60873091);辽宁省自然科学基金资助项目(20072032);沈阳市科学技术计划资助项目(1081235-1-00)
{{custom_fund}}
PDF(734 KB)
