AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
Hierarchical phrase pairs, which can be learned without any syntactically-annotated training data, improve translation accuracy significantly compared with a state-of-the-art phrase-based system

A hierarchical phrase-based model for statistical machine translation

ACL, pp.263-270, (2005)

被引用1291|浏览241
EI
下载 PDF 全文
引用
微博一下

摘要

We present a statistical phrase-based translation model that uses hierarchical phrases---phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information. Thus it can be seen as a shift to the formal machinery of syntax-based translation systems withou...更多

代码

数据

简介
  • The alignment template translation model (Och and Ney, 2004) and related phrase-based models advanced the previous state of the art by moving from words to phrases as the basic unit of translation.
  • Phrases, which can be any substring and not necessarily phrases in any syntactic theory, allow these models to learn local reorderings, translation of short idioms, or insertions and deletions that are sensitive to local context.
  • They are a simple and powerful mechanism for machine translation.
  • The basic architecture of phrase segmentation, phrase reordering, and phrase translation remains the same
重点内容
  • The alignment template translation model (Och and Ney, 2004) and related phrase-based models advanced the previous state of the art by moving from words to phrases as the basic unit of translation
  • The translation model P( f | e) “encodes” e into f by the following steps: 1. segment e into phrases e1 · · · eI, typically with a uniform distribution over segmentations; 2. reorder the ei according to some distortion model; 3. translate each of the ei into French phrases according to a model P( f | e) estimated from the training data
  • Hierarchical phrase pairs, which can be learned without any syntactically-annotated training data, improve translation accuracy significantly compared with a state-of-the-art phrase-based system
方法
  • The authors' experiments were on Mandarin-to-English translation.
  • The authors used the 2002 NIST MT evaluation test set as the development set, and the 2003 test set as the test set.
  • The authors' evaluation metric was BLEU (Papineni et al, 2002), as calculated by the NIST script with its default settings, which is to perform case-insensitive matching of n-grams up to n = 4, and to use the shortest reference sentence for the brevity penalty.
  • The results of the experiments are summarized in Table 1
结果
  • The authors' system achieves an absolute improvement of 0.02 over the baseline (7.5% relative), without using any additional training data.
  • This difference is statistically significant (p < 0.01).5
结论
  • Hierarchical phrase pairs, which can be learned without any syntactically-annotated training data, improve translation accuracy significantly compared with a state-of-the-art phrase-based system.
  • The authors' primary goal for the future is to move towards a more syntactically-motivated grammar, whether by automatic methods to induce syntactic categories, or by better integration of parsers trained on annotated data.
  • This would potentially improve both accuracy and efficiency.
  • Streamlining the grammar would allow further experimentation in these directions
总结
  • Introduction:

    The alignment template translation model (Och and Ney, 2004) and related phrase-based models advanced the previous state of the art by moving from words to phrases as the basic unit of translation.
  • Phrases, which can be any substring and not necessarily phrases in any syntactic theory, allow these models to learn local reorderings, translation of short idioms, or insertions and deletions that are sensitive to local context.
  • They are a simple and powerful mechanism for machine translation.
  • The basic architecture of phrase segmentation, phrase reordering, and phrase translation remains the same
  • Methods:

    The authors' experiments were on Mandarin-to-English translation.
  • The authors used the 2002 NIST MT evaluation test set as the development set, and the 2003 test set as the test set.
  • The authors' evaluation metric was BLEU (Papineni et al, 2002), as calculated by the NIST script with its default settings, which is to perform case-insensitive matching of n-grams up to n = 4, and to use the shortest reference sentence for the brevity penalty.
  • The results of the experiments are summarized in Table 1
  • Results:

    The authors' system achieves an absolute improvement of 0.02 over the baseline (7.5% relative), without using any additional training data.
  • This difference is statistically significant (p < 0.01).5
  • Conclusion:

    Hierarchical phrase pairs, which can be learned without any syntactically-annotated training data, improve translation accuracy significantly compared with a state-of-the-art phrase-based system.
  • The authors' primary goal for the future is to move towards a more syntactically-motivated grammar, whether by automatic methods to induce syntactic categories, or by better integration of parsers trained on annotated data.
  • This would potentially improve both accuracy and efficiency.
  • Streamlining the grammar would allow further experimentation in these directions
表格
  • Table1: Results on baseline system and hierarchical system, with and without constituent feature
  • Table2: Feature weights obtained by minimum-error-rate training (normalized so that absolute values sum to one). Word = word penalty; Phr = phrase penalty. Note that we have inverted the sense of Pharaoh’s phrase penalty so that a positive weight indicates a penalty
Download tables as Excel
基金
  • This work was partially supported by ONR MURI contract FCPO.810548265 and Department of Defense contract RD-02-5700
引用论文
  • A. V. Aho and J. D. Ullman. 1969. Syntax directed translations and the pushdown assembler. Journal of Computer and System Sciences, 3:37–56.
    Google ScholarLocate open access versionFindings
  • Daniel M. Bikel and David Chiang. 2000. Two statistical parsing models applied to the Chinese Treebank. In Proceedings of the Second Chinese Language Processing Workshop, pages 1–6.
    Google ScholarLocate open access versionFindings
  • Hans Ulrich Block. 2000. Example-based incremental synchronous interpretation. In Wolfgang Wahlster, editor, Verbmobil: Foundations of Speech-to-Speech Translation, pages 411–417. Springer-Verlag, Berlin.
    Google ScholarLocate open access versionFindings
  • Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. 1993. The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19:263–311.
    Google ScholarLocate open access versionFindings
  • Stanley F. Chen and Joshua Goodman. 1998. An empirical study of smoothing techniques for language modeling. Technical Report TR-10-98, Harvard University Center for Research in Computing Technology.
    Google ScholarFindings
  • Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase-based translation. In Proceedings of HLT-NAACL 2003, pages 127–133.
    Google ScholarLocate open access versionFindings
  • Philipp Koehn. 2003. Noun Phrase Translation. Ph.D. thesis, University of Southern California.
    Google ScholarFindings
  • Philipp Koehn. 2004a. Pharaoh: a beam search decoder for phrase-based statistical machine translation models. In Proceedings of the Sixth Conference of the Association for Machine Translation in the Americas, pages 115–124.
    Google ScholarLocate open access versionFindings
  • Philipp Koehn. 2004b. Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 388–395.
    Google ScholarLocate open access versionFindings
  • Shankar Kumar, Yonggang Deng, and William Byrne. 2005. A weighted finite state transducer translation template model for statistical machine translation. Natural Language Engineering. To appear.
    Google ScholarLocate open access versionFindings
  • Daniel Marcu and William Wong. 2002. A phrasebased, joint probability model for statistical machine translation. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 133–139.
    Google ScholarLocate open access versionFindings
  • Franz Josef Och and Hermann Ney. 2000. Improved statistical alignment models. In Proceedings of the 38th Annual Meeting of the ACL, pages 440–447.
    Google ScholarLocate open access versionFindings
  • Franz Josef Och and Hermann Ney. 2002. Discriminative training and maximum entropy models for statistical machine translation. In Proceedings of the 40th Annual Meeting of the ACL, pages 295–302.
    Google ScholarLocate open access versionFindings
  • Franz Josef Och and Hermann Ney. 2004. The alignment template approach to statistical machine translation. Computational Linguistics, 30:417–449.
    Google ScholarLocate open access versionFindings
  • Franz Josef Och, Ignacio Thayer, Daniel Marcu, Kevin Knight, Dragos Stefan Munteanu, Quamrul Tipu, Michel Galley, and Mark Hopkins. 2004. Arabic and Chinese MT at USC/ISI. Presentation given at NIST Machine Translation Evaluation Workshop.
    Google ScholarFindings
  • Franz Josef Och. 2003. Minimum error rate training in statistical machine translation. In Proceedings of the 41st Annual Meeting of the ACL, pages 160–167.
    Google ScholarLocate open access versionFindings
  • Kishore Papineni, Salim Roukos, Todd Ward, and WeiJing Zhu. 2002. B: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the ACL, pages 311–318.
    Google ScholarLocate open access versionFindings
  • Andreas Stolcke. 2002. SRILM – an extensible language modeling toolkit. In Proceedings of the International Conference on Spoken Language Processing, volume 2, pages 901–904.
    Google ScholarLocate open access versionFindings
  • Dekai Wu. 1997. Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Computational Linguistics, 23:377–404.
    Google ScholarLocate open access versionFindings
  • Kenji Yamada and Kevin Knight. 2001. A syntax-based statistical translation model. In Proceedings of the 39th Annual Meeting of the ACL, pages 523–530.
    Google ScholarLocate open access versionFindings
  • Richard Zens and Hermann Ney. 2004. Improvements in phrase-based statistical machine translation. In Proceedings of HLT-NAACL 2004, pages 257–264.
    Google ScholarLocate open access versionFindings
  • Ying Zhang, Stephan Vogel, and Alex Waibel. 2004. Interpreting BLEU/NIST scores: How much improvement do we need to have a better system? In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC), pages 2051– 2054.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

最佳论文
2005年, 荣获ACL的最佳论文奖
标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科