Proceedings

An Introduction to String Re-Writing Kernel

Download BibTeX Cite

Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 2982-2985.

© 2013 International Joint Conferences on Artificial Intelligence

Abstract

Learning for sentence rewriting is a fundamental task in natural language processing and information retrieval. In this paper, we propose a new class of kernel functions, referred to as string rewriting kernel, to address the problem. A string re-writing kernel measures the similarity between two pairs of strings. It can capture the lexical and structural similarity between sentence pairs without the need of constructing syntactic trees. We further propose an instance of string re-writing kernel which can be computed efficiently. Experimental results on benchmark datasets show that our method can achieve comparable results with state-of-the-art methods on two sentence re-writing learning tasks: paraphrase identification and recognizing textual entailment.

  1. [Barzilay and Lee, 2003] R. Barzilay and L. Lee. Learning to paraphrase: An unsupervised approach using multiple- sequence alignment. In Proceedings of the 2003 Confer- ence of the North American Chapter of the Association for Computational Linguistics on Human Language Technol- ogy, pages 16-23, 2003.
  2. [Basilico and Hofmann, 2004] J. Basilico and T. Hofmann. Unifying collaborative and content-based filtering. In Pro- ceedings of the twenty-first international conference on Machine learning, 2004.
  3. [Ben-Hur and Noble, 2005] A. Ben-Hur and W.S. Noble. Kernel methods for predicting protein-protein interac- tions. Bioinformatics, 21:i38-i46, 2005.
  4. [Bu et al., 2012] Fan Bu, Hang Li, and Xiaoyan Zhu. String re-writing kernel. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 449-458, 2012.
  5. [Chang and Lin, 2011] C. Chang and C. Lin. Libsvm: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3):27:1-27:27, 2011.
  6. [Das and Smith, 2009] D. Das and N.A. Smith. Paraphrase identification as probabilistic quasi-synchronous recogni- tion. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 468-476, 2009.
  7. [de Marneffe et al., 2006] M. de Marneffe, B. MacCartney, T. Grenager, D. Cer, Rafferty A., and C.D. Manning. Learning to distinguish valid textual entailments. In Proc. of the Second PASCAL Challenges Workshop, pages 468- 476, 2006.
  8. [Dolan and Brockett, 2005] W.B. Dolan and C. Brockett. Automatically constructing a corpus of sentential para- phrases. In Proc. of IWP, 2005.
  9. [Harmeling, 2007] S. Harmeling. An extensible probabilis- tic transformation-based approach to the third recognizing textual entailment challenge. In Proceedings of the ACL- PASCAL Workshop on Textual Entailment and Paraphras- ing, pages 137-142, 2007.
  10. [Heilman and Smith, 2010] M. Heilman and N.A. Smith. Tree edit models for recognizing textual entailments, para- phrases, and answers to questions. In Proc. of Human Lan- guage Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computa- tional Linguistics, pages 1011-1019, 2010.
  11. [Kashima et al., 2009] H. Kashima, S. Oyama, Y. Yaman- ishi, and K. Tsuda. On pairwise kernels: An efficient al- ternative and generalization analysis. Advances in Knowl- edge Discovery and Data Mining, pages 1030-1037, 2009.
  12. [Leslie and Kuang, 2004] C. Leslie and R. Kuang. Fast string kernels using inexact matching for protein se- quences. The Journal of Machine Learning Research, 5:1435-1455, 2004.
  13. [Leslie et al., 2002] C. Leslie, E. Eskin, and W.S. Noble. The spectrum kernel: a string kernel for svm protein classifica- tion. In Pacific Symposium on Biocomputing, volume 575, pages 564-575, 2002.
  14. [Lin and Pantel, 2001] D. Lin and P. Pantel. Dirt-discovery of inference rules from text. In Proc. of ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2001.
  15. [Lintean and Rus, 2011] M. Lintean and V. Rus. Dissimi- larity kernels for paraphrase identification. In Proc. of Twenty-Fourth International FLAIRS Conference, 2011.
  16. [Lodhi et al., 2002] H. Lodhi, C. Saunders, J. Shawe-Taylor, N. Cristianini, and C. Watkins. Text classification using string kernels. The Journal of Machine Learning Research, 2:419-444, 2002.
  17. [MacCartney and Manning, 2008] B. MacCartney and C.D. Manning. Modeling semantic containment and exclusion in natural language inference. In Proceedings of the 22nd International Conference on Computational Linguistics, volume 1, pages 521-528, 2008.
  18. [Moschitti and Zanzotto, 2007] A. Moschitti and F.M. Zan- zotto. Fast and effective kernels for relational learning from texts. In Proceedings of the 24th Annual Interna- tional Conference on Machine Learning, 2007.
  19. [Qiu et al., 2006] L. Qiu, M.Y. Kan, and T.S. Chua. Para- phrase recognition via dissimilarity significance classifica- tion. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 18-26, 2006.
  20. [Quirk et al., 2004] C. Quirk, C. Brockett, and W. Dolan. Monolingual machine translation for paraphrase genera- tion. In Proceedings of EMNLP 2004, pages 142-149, 2004.
  21. [Socher et al., 2011] Richard Socher, Eric H Huang, Jeffrey Pennington, Andrew Y Ng, and Christopher D Manning. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. Advances in Neural Information Processing Systems, 24:801-809, 2011.
  22. [Wan et al., 2006] S. Wan, M. Dras, R. Dale, and C. Paris. Using dependency-based features to take the "para-farce" out of paraphrase. In Proc. of the Australasian Language Technology Workshop, pages 131-138, 2006.
  23. [Zanzotto et al., 2007] F.M. Zanzotto, M. Pennacchiotti, and A. Moschitti. Shallow semantics in fast textual entailment rule learners. In Proceedings of the ACL-PASCAL work- shop on textual entailment and paraphrasing, pages 72- 77, 2007.
  24. [Zhang and Patrick, 2005] Y. Zhang and J. Patrick. Para- phrase identification by text canonicalization. In Proceed- ings of the Australasian Language Technology Workshop, pages 160-166, 2005.

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

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