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
We propose a novel string-todependency algorithm for statistical machine translation

A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model

ACL, pp.577-585, (2008)

被引用280|浏览246
EI
下载 PDF 全文
引用
微博一下

摘要

In this paper, we propose a novel string-to- dependency algorithm for statistical machine translation. With this new framework, we em- ploy a target dependency language model dur- ing decoding to exploit long distance word relations, which are unavailable with a tra- ditional n-gram language model. Our ex- periments show that the string-t...更多

代码

数据

简介
  • Hierarchical methods have been successfully applied to Statistical Machine Translation (Graehl and Knight, 2004; Chiang, 2005; Ding and Palmer, 2005; Quirk et al, 2005).
  • Chiang (2007) showed that the Hiero system achieved about 1 to 3 point improvement in BLEU on the NIST 03/04/05 Chinese-English evaluation sets compared to a start-of-the-art phrasal system.
  • The authors restrict the target side to the so called wellformed dependency structures, in order to cover a large set of non-constituent transfer rules (Marcu et al, 2006), and enable efficient decoding through dynamic programming.
  • The authors incorporate a dependency language model during decoding, in order to exploit long-distance word relations which are unavailable with a traditional n-gram language model on target strings
重点内容
  • Hierarchical methods have been successfully applied to Statistical Machine Translation (Graehl and Knight, 2004; Chiang, 2005; Ding and Palmer, 2005; Quirk et al, 2005)
  • Chiang (2007) showed that the Hiero system achieved about 1 to 3 point improvement in BLEU on the NIST 03/04/05 Chinese-English evaluation sets compared to a start-of-the-art phrasal system
  • We restrict the target side to the so called wellformed dependency structures, in order to cover a large set of non-constituent transfer rules (Marcu et al, 2006), and enable efficient decoding through dynamic programming
  • We incorporate a dependency language model during decoding, in order to exploit long-distance word relations which are unavailable with a traditional n-gram language model on target strings
  • We propose a novel string-todependency algorithm for statistical machine translation
方法
  • The authors carried out experiments on three models. baseline: replication of the Hiero system. filtered: a string-to-string MT system as in baseline.
  • The authors use dependency structures instead of strings; the comparison will show the contribution of using dependency information in decoding
结果
  • The rule size increased a little bit after incorporating dependency structures in rules, the size of string-to-dependency rule set is less than 20% of the baseline rule set size.
结论
  • The well-formed dependency structures defined here are similar to the data structures in previous work on mono-lingual parsing (Eisner and Satta, 1999; McDonald et al, 2005).
  • Charniak et al (2003) described a two-step stringto-CFG-tree translation model which employed a syntax-based language model to select the best translation from a target parse forest built in the first step.
  • Since the dependency LM models structures over target words directly based on dependency trees, the authors can build a single-step system.
  • This dependency LM can be used in hierarchical MT systems using lexicalized CFG trees.Conclusions and Future.
  • The authors believe that the fixed and floating structures proposed in this paper can be extended to model predicates and arguments
总结
  • Introduction:

    Hierarchical methods have been successfully applied to Statistical Machine Translation (Graehl and Knight, 2004; Chiang, 2005; Ding and Palmer, 2005; Quirk et al, 2005).
  • Chiang (2007) showed that the Hiero system achieved about 1 to 3 point improvement in BLEU on the NIST 03/04/05 Chinese-English evaluation sets compared to a start-of-the-art phrasal system.
  • The authors restrict the target side to the so called wellformed dependency structures, in order to cover a large set of non-constituent transfer rules (Marcu et al, 2006), and enable efficient decoding through dynamic programming.
  • The authors incorporate a dependency language model during decoding, in order to exploit long-distance word relations which are unavailable with a traditional n-gram language model on target strings
  • Methods:

    The authors carried out experiments on three models. baseline: replication of the Hiero system. filtered: a string-to-string MT system as in baseline.
  • The authors use dependency structures instead of strings; the comparison will show the contribution of using dependency information in decoding
  • Results:

    The rule size increased a little bit after incorporating dependency structures in rules, the size of string-to-dependency rule set is less than 20% of the baseline rule set size.
  • Conclusion:

    The well-formed dependency structures defined here are similar to the data structures in previous work on mono-lingual parsing (Eisner and Satta, 1999; McDonald et al, 2005).
  • Charniak et al (2003) described a two-step stringto-CFG-tree translation model which employed a syntax-based language model to select the best translation from a target parse forest built in the first step.
  • Since the dependency LM models structures over target words directly based on dependency trees, the authors can build a single-step system.
  • This dependency LM can be used in hierarchical MT systems using lexicalized CFG trees.Conclusions and Future.
  • The authors believe that the fixed and floating structures proposed in this paper can be extended to model predicates and arguments
表格
  • Table1: Number of transfer rules
  • Table2: BLEU and TER scores on the test set
Download tables as Excel
基金
  • This work was supported by DARPA/IPTO Contract No HR0011-06-C-0022 under the GALE program
研究对象与分析
children: 2
We use a 5-tuple (LF, LN, h, RN, RF ) to represent the category of a dependency structure. h represents the head. LF and RF represent the farthest two children on the left and right sides respectively. Similarly, LN and RN represent the nearest two children on the left and right sides respectively

children: 2
LF and RF represent the farthest two children on the left and right sides respectively. Similarly, LN and RN represent the nearest two children on the left and right sides respectively. The three types of categories are as follows

引用论文
  • I. Bulyko, S. Matsoukas, R. Schwartz, L. Nguyen, and J. Makhoul. 2007. Language model adaptation in machine translation from speech. In Proceedings of the 32nd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP).
    Google ScholarLocate open access versionFindings
  • E. Charniak, K. Knight, and K. Yamada. 2003. Syntaxbased language models for statistical machine translation. In Proceedings of MT Summit IX.
    Google ScholarLocate open access versionFindings
  • D. Chiang. 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of the 43th Annual Meeting of the Association for Computational Linguistics (ACL).
    Google ScholarLocate open access versionFindings
  • D. Chiang. 2007. Hierarchical phrase-based translation. Computational Linguistics, 33(2).
    Google ScholarLocate open access versionFindings
  • S. DeNeefe, K. Knight, W. Wang, and D. Marcu. 2007. What can syntax-based mt learn from phrase-based mt? In Proceedings of the 2007 Conference of Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • Y. Ding and M. Palmer. 2005. Machine translation using probabilistic synchronous dependency insertion grammars. In Proceedings of the 43th Annual Meeting of the Association for Computational Linguistics (ACL), pages 541–548, Ann Arbor, Michigan, June.
    Google ScholarLocate open access versionFindings
  • J. Eisner and G. Satta. 1999. Efficient parsing for bilexical context-free grammars and head automaton grammars. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL).
    Google ScholarLocate open access versionFindings
  • H. Fox. 2002. Phrasal cohesion and statistical machine translation. In Proceedings of the 2002 Conference of Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • M. Galley, M. Hopkins, K. Knight, and D. Marcu. 2004. What’s in a translation rule? In Proceedings of the 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • M. Galley, J. Graehl, K. Knight, D. Marcu, S. DeNeefea, W. Wang, and I. Thayer. 2006. Scalable inference and training of context-rich syntactic models. In COLINGACL ’06: Proceedings of 44th Annual Meeting of the Association for Computational Linguistics and 21st Int. Conf. on Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • J. Graehl and K. Knight. 2004. Training tree transducers. In Proceedings of the 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • L. Huang and D. Chiang. 2005. Better k-best parsing. In Proceedings of the 9th International Workshop on Parsing Technologies.
    Google ScholarLocate open access versionFindings
  • D. Magerman. 1995. Statistical decision-tree models for parsing. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • D. Marcu, W. Wang, A. Echihabi, and K. Knight. 2006. SPMT: Statistical machine translation with syntactified target language phraases. In Proceedings of the 2006 Conference of Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • R. McDonald, K. Crammer, and F. Pereira. 2005. Online large-margin training of dependency parsers. In Proceedings of the 43th Annual Meeting of the Association for Computational Linguistics (ACL).
    Google ScholarLocate open access versionFindings
  • F. J. Och and H. Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1).
    Google ScholarLocate open access versionFindings
  • F. J. Och. 2003. Minimum error rate training for statistical machine translation. In Erhard W. Hinrichs and Dan Roth, editors, Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL), pages 160–167, Sapporo, Japan, July.
    Google ScholarLocate open access versionFindings
  • M. Palmer, D. Gildea, and P. Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1).
    Google ScholarLocate open access versionFindings
  • K. Papineni, S. Roukos, and T. Ward. 2001. Bleu: a method for automatic evaluation of machine translation. IBM Research Report, RC22176.
    Google ScholarLocate open access versionFindings
  • C. Quirk, A. Menezes, and C. Cherry. 2005. Dependency treelet translation: Syntactically informed phrasal SMT. In Proceedings of the 43th Annual Meeting of the Association for Computational Linguistics (ACL), pages 271–279, Ann Arbor, Michigan, June.
    Google ScholarLocate open access versionFindings
  • S. Shieber and Y. Schabes. 1990. Synchronous tree adjoining grammars. In Proceedings of COLING ’90: The 13th Int. Conf. on Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • M. Snover, B. Dorr, R. Schwartz, L. Micciulla, and J. Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of Association for Machine Translation in the Americas.
    Google ScholarLocate open access versionFindings
  • W. Wang, K. Knight, and D. Marcu. 2007. Binarizing syntax trees to improve syntax-based machine translation accuracy. In Proceedings of the 2007 Conference of Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • P. Xu, C. Chelba, and F. Jelinek. 2002. A study on richer syntactic dependencies for structured language modeling. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL).
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

最佳论文
2008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