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
A semantic parser is learned given a set of training sentences and their correct logical forms using standard statistical machine translation techniques

Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus

ACL, (2007)

被引用342|浏览242
EI
下载 PDF 全文
引用
微博一下

摘要

This paper presents the first empirical results to our knowledge on learning synchronous grammars that generate logical forms. Using statistical machine translation techniques, a semantic parser based on a synchronous context-free grammar augmented with - operators is learned given a set of training sentences and their correct logical for...更多

代码

数据

0
简介
  • Developed as a theory of compiling programming languages (Aho and Ullman, 1972), synchronous grammars have seen a surge of interest remars in semantic parsing and NL generation is limited to simple MRLs that are free of logical variables
  • This is because grammar formalisms such as cently in the statistical machine translation (SMT) SCFG do not have a principled mechanism for hancommunity as a way of formalizing syntax-based dling logical variables.
  • Development of such a functional language is non-trivial, and as the authors will see, logical languages can be more appropriate for certain domains
重点内容
  • Introduction is translated into an

    natural languages (NL) (Wong and Mooney, 2007)
  • Developed as a theory of compiling programming languages (Aho and Ullman, 1972), synchronous grammars have seen a surge of interest remars in semantic parsing and NL generation is limited to simple meaning-representation language (MRL) that are free of logical variables
  • In generating multiple parse trees in a single deriva- based on predicate logic, where logical variables tion, synchronous grammars are ideal for model- play an important role (Blackburn and Bos, 2005)
  • We have presented λ-WASP, a semantic parsing algorithm based on a λ-SCFG that generates logical forms using λ-calculus
  • A semantic parser is learned given a set of training sentences and their correct logical forms using standard statistical machine translation (SMT) techniques
结果
  • It is found that conjunct regrouping improves recall (p < 0.01 based on the paired t-test), and the use of two-level rules in the maximum-entropy model improves precision and recall (p < 0.05).
结论
  • The authors have presented λ-WASP, a semantic parsing algorithm based on a λ-SCFG that generates logical forms using λ-calculus.
  • A semantic parser is learned given a set of training sentences and their correct logical forms using standard SMT techniques.
  • This work shows that it is possible to use standard SMT methods in tasks where logical forms are involved.
  • It should be straightforward to adapt λ-WASP to the NL generation task—all one needs is a decoder that can handle input logical forms.
  • Other tasks that can potentially benefit from (%) Precision Recall λ-WASP 91.95 86.59
总结
  • Introduction:

    Developed as a theory of compiling programming languages (Aho and Ullman, 1972), synchronous grammars have seen a surge of interest remars in semantic parsing and NL generation is limited to simple MRLs that are free of logical variables
  • This is because grammar formalisms such as cently in the statistical machine translation (SMT) SCFG do not have a principled mechanism for hancommunity as a way of formalizing syntax-based dling logical variables.
  • Development of such a functional language is non-trivial, and as the authors will see, logical languages can be more appropriate for certain domains
  • Results:

    It is found that conjunct regrouping improves recall (p < 0.01 based on the paired t-test), and the use of two-level rules in the maximum-entropy model improves precision and recall (p < 0.05).
  • Conclusion:

    The authors have presented λ-WASP, a semantic parsing algorithm based on a λ-SCFG that generates logical forms using λ-calculus.
  • A semantic parser is learned given a set of training sentences and their correct logical forms using standard SMT techniques.
  • This work shows that it is possible to use standard SMT methods in tasks where logical forms are involved.
  • It should be straightforward to adapt λ-WASP to the NL generation task—all one needs is a decoder that can handle input logical forms.
  • Other tasks that can potentially benefit from (%) Precision Recall λ-WASP 91.95 86.59
表格
  • Table1: Performance of various parsing algorithms on the larger GEOQUERY corpus
  • Table2: Performance of λ-WASP with certain components of the algorithm removed
Download tables as Excel
基金
  • This work was supported by a gift from Google Inc
引用论文
  • A. V. Aho and J. D. Ullman. 1972. The Theory of Parsing, Translation, and Compiling. Prentice Hall, Englewood Cliffs, NJ.
    Google ScholarFindings
  • S. Bayer, J. Burger, W. Greiff, and B. Wellner. 2004. The MITRE logical form generation system. In Proc. of Senseval-3, Barcelona, Spain, July.
    Google ScholarLocate open access versionFindings
  • P. Blackburn and J. Bos. 2005. Representation and Inference for Natural Language: A First Course in Computational Semantics. CSLI Publications, Stanford, CA.
    Google ScholarFindings
  • J. Bos. 2005. Towards wide-coverage semantic interpretation. In Proc. of IWCS-05, Tilburg, The Netherlands, January.
    Google ScholarLocate open access versionFindings
  • D. Chiang. 200A hierarchical phrase-based model for statistical machine translation. In Proc. of ACL-05, pages 263– 270, Ann Arbor, MI, June.
    Google ScholarLocate open access versionFindings
  • M. Collins and T. Koo. 2005. Discriminative reranking for natural language parsing. Computational Linguistics, 31(1):25–69.
    Google ScholarLocate open access versionFindings
  • M. Galley, J. Graehl, K. Knight, D. Marcu, S. DeNeefe, W. Wang, and I. Thayer. 2006. Scalable inference and training of context-rich syntactic translation models. In Proc. of COLING/ACL-06, pages 961–968, Sydney, Australia, July.
    Google ScholarLocate open access versionFindings
  • R. Ge and R. J. Mooney. 2005. A statistical semantic parser that integrates syntax and semantics. In Proc. of CoNLL-05, pages 9–16, Ann Arbor, MI, July.
    Google ScholarLocate open access versionFindings
  • H. P. Grice. 1975. Logic and conversation. In P. Cole and J. Morgan, eds., Syntax and Semantics 3: Speech Acts, pages 41–58. Academic Press, New York.
    Google ScholarLocate open access versionFindings
  • A. K. Joshi and K. Vijay-Shanker. 2001. Compositional semantics with lexicalized tree-adjoining grammar (LTAG): How much underspecification is necessary? In H. Bunt et al., eds., Computing Meaning, volume 2, pages 147–163. Kluwer Academic Publishers, Dordrecht, The Netherlands.
    Google ScholarLocate open access versionFindings
  • R. Montague. 1970. Universal grammar. Theoria, 36:373–398.
    Google ScholarLocate open access versionFindings
  • F. J. Och and H. Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1):19–51.
    Google ScholarLocate open access versionFindings
  • K. A. Papineni, S. Roukos, and R. T. Ward. 1997. Featurebased language understanding. In Proc. of EuroSpeech-97, pages 1435–1438, Rhodes, Greece.
    Google ScholarLocate open access versionFindings
  • W. Schuler. 2003. Using model-theoretic semantic interpretation to guide statistical parsing and word recognition in a spoken language interface. In Proc. of ACL-03, pages 529– 536.
    Google ScholarLocate open access versionFindings
  • Y. W. Wong and R. J. Mooney. 2006. Learning for semantic parsing with statistical machine translation. In Proc. of HLT/NAACL-06, pages 439–446, New York City, NY.
    Google ScholarLocate open access versionFindings
  • Y. W. Wong and R. J. Mooney. 2007. Generation by inverting a semantic parser that uses statistical machine translation. In Proc. of NAACL/HLT-07, Rochester, NY, to appear.
    Google ScholarLocate open access versionFindings
  • D. Wu. 1997. Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Computational Linguistics, 23(3):377–403.
    Google ScholarLocate open access versionFindings
  • K. Yamada and K. Knight. 2001. A syntax-based statistical translation model. In Proc. of ACL-01, pages 523–530, Toulouse, France.
    Google ScholarLocate open access versionFindings
  • J. M. Zelle and R. J. Mooney. 1996. Learning to parse database queries using inductive logic programming. In Proc. of AAAI-96, pages 1050–1055, Portland, OR, August.
    Google ScholarLocate open access versionFindings
  • L. S. Zettlemoyer and M. Collins. 2005. Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars. In Proc. of UAI-05, Edinburgh, Scotland, July.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

最佳论文
2007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