Proceedings

Statistical Parsing with Probabilistic Symbol-Refined Tree Substitution Grammars

Download BibTeX Cite

Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 3082-3085.

© 2013 International Joint Conferences on Artificial Intelligence

Abstract

We present probabilistic Symbol-Refined Tree Substitution Grammars (SR-TSG) for statistical parsing of natural language sentences. An SR-TSG is an extension of the conventional TSG model where each nonterminal symbol can be refined (subcategorized) to fit the training data. Our probabilistic model is consistent based on the hierarchical Pitman-Yor Process to encode backoff smoothing from a fine-grained SR-TSG to simpler CFG rules, thus all grammar rules can be learned from training data in a fully automatic fashion. Our SR-TSG parser achieves the state-of-the-art performance on the Wall Street Journal (WSJ) English Penn Treebank data.

  1. [Bansal and Klein, 2010] Mohit Bansal and Dan Klein. Sim- ple, Accurate Parsing with an All-Fragments Grammar. In In Proc. of ACL, pages 1098-1107, 2010.
  2. [Charniak and Johnson, 2005] Eugene Charniak and Mark Johnson. Coarse-to-Fine n-Best Parsing and MaxEnt Dis- criminative Reranking. In Proc. of ACL, 1:173-180, 2005.
  3. [Cohn and Lapata, 2009] Trevor Cohn and Mirella Lapata. Sentence Compression as Tree Transduction. Journal of Artificial Intelligence Research, 34:637-674, 2009.
  4. [Cohn et al., 2010] Trevor Cohn, Phil Blunsom, and Sharon Goldwater. Inducing Tree-Substitution Grammars. Jour- nal of Machine Learning Research, 11:3053-3096, 2010.
  5. [Fossum and Knight, 2009] Victoria Fossum and Kevin Knight. Combining Constituent Parsers. In Proc. of HLT-NAACL, pages 253-256, 2009.
  6. [Huang, 2008] Liang Huang. Forest Reranking : Discrimi- native Parsing with Non-Local Features. In Proc. of ACL, 19104:0, 2008.
  7. [Johnson and Goldwater, 2009] Mark Johnson and Sharon Goldwater. Improving nonparameteric Bayesian infer- ence: experiments on unsupervised word segmentation with adaptor grammars. In In Proc. of HLT-NAACL, pages 317-325, 2009.
  8. [Johnson et al., 2007a] Mark Johnson, Thomas L Griffiths, and Sharon Goldwater. Adaptor Grammars : A Framework for Specifying Compositional Nonparametric Bayesian Models. Advances in Neural Information Processing Sys- tems 19, 19:641-648, 2007.
  9. [Johnson et al., 2007b] Mark Johnson, Thomas L Griffiths, and Sharon Goldwater. Bayesian Inference for PCFGs via Markov chain Monte Carlo. In In Proc. of HLT-NAACL, pages 139-146, 2007.
  10. [Johnson, 1998] Mark Johnson. PCFG Models of Linguistic Tree Representations. Computational Linguistics, 24:613- 632, 1998.
  11. [Klein and Manning, 2003] Dan Klein and Christopher D Manning. Accurate Unlexicalized Parsing. In Proc. of ACL, 1:423-430, 2003.
  12. [Lari and Young, 1991] K Lari and S J Young. Applications of Stochastic Context-Free Grammars Using the Inside- Outside Algorithm. Computer Speech and Language, 5:237-257, 1991.
  13. [Marcus et al., 1993] Mitchell P Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. Building a Large Anno- tated Corpus of English: The Penn Treebank. Computa- tional Linguistics, 19:313-330, 1993.
  14. [Petrov et al., 2006] Slav Petrov, Leon Barrett, Romain Thibaux, and Dan Klein. Learning Accurate, Compact, and Interpretable Tree Annotation. In Proc. of ACL, pages 433-440, 2006.
  15. [Petrov, 2010] Slav Petrov. Products of Random Latent Vari- able Grammars. In Proc. of HLT-NAACL, pages 19-27, 2010.
  16. [Pitman and Yor, 1997] Jim Pitman and Marc Yor. The two- parameter Poisson-Dirichlet distribution derived from a stable subordinator. The Annals of Probability, 25:855- 900, 1997.
  17. [Post and Gildea, 2009] Matt Post and Daniel Gildea. Bayesian Learning of a Tree Substitution Grammar. In In Proc. of ACL-IJCNLP, pages 45-48, 2009.
  18. [Shindo et al., 2012] Hiroyuki Shindo, Yusuke Miyao, Aki- nori Fujino, Masaaki Nagata. Bayesian Symbol-Refined Tree Substitution Grammars for Syntactic Parsing. In Proc. of ACL, pages 440-448, 2012.
  19. [Tenenbaum et al., 2009] J Tenenbaum, TJ O'Donnell, and ND Goodman. Fragment Grammars: Exploring Computa- tion and Reuse in Language. MIT Computer Science and Artificial Intelligence Laboratory Technical Report Series, 2009.
  20. [Zhang et al., 2009] Hui Zhang, Min Zhang, Chew Lim Tan, and Haizhou Li. K-Best Combination of Syntactic Parsers. In Proc. of EMNLP, pages 1552-1560, 2009.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards