Coreference Resolution Using Verbs Knowledge
الموضوعات :hasan zafari 1 , Maryam hourali 2 , Heshaam Faili 3
1 - Malek-Ashtar University of Technology
2 - Malek-Ashtar university of Technology
3 - Tehran
الکلمات المفتاحية: Coreference resolution , anaphora resolution , semantically related verbs , text inference , NLP,
ملخص المقالة :
Coreference resolution is the problem of determining which mention in a text refer to the same entities, and is a crucial and difficult step in every natural language processing task. Despite the efforts that have been made in the past to solve this problem, its performance still does not meet today’s applications requirements. Given the importance of the verbs in sentences, in this work we tried to incorporate three types of their information on coreference resolution problem, namely, selectional restriction of verbs on their arguments, semantic relation between verb pairs, and the truth that arguments of a verb cannot be coreferent of each other. As a needed resource for supporting our model, we generate a repository of semantic relations between verb pairs automatically using Distributional Memory (DM), a state-of-the-art framework for distributional semantics. This resource consists of pairs of verbs associated with their probable arguments, their role mapping, and significance scores based on our measures. Our proposed model for coreference resolution encodes verbs’ knowledge with Markov logic network rules on top of deterministic Stanford coreference resolution system. Experiment results show that this semantic layer can improve the recall of the Stanford system while preserves its precision and improves it slightly.
[1] D. Bean and E. Riloff, “Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution,” in HLT-NAACL, 2004, pp. 297–304.
[2] H. Lee, M. Recasens, A. Chang, and M. Surdeanu, “Joint entity and event coreference resolution across documents,” in Association for Computational Linguistics, 2012.
[3] N. Chambers and D. Jurafsky, “Unsupervised Learning of Narrative Schemas and their Participants,” Proc. Jt. Conf. 47th Annu. Meet. ACL-IJCNLP 4th Int. Jt. Conf. Nat. Lang. Process. AFNLP, vol. 2, no. August, p. 602, 2009.
[4] N. Chambers and D. Jurafsky, “Unsupervised learning of narrative event chains,” Proc. Assoc. Comput. Linguist., vol. 31, no. 14, pp. 789–797, 2008.
[5] M. Bansal and D. Klein, “Coreference Semantics from Web Features,” Proc. 50th Annu. Meet. Assoc. Comput. Linguist., no. July, pp. 389–398, 2012.
[6] L. Zilles and D. S. Weld, “Joint Coreference Resolution and Named-Entity Linking with Multi-pass Sieves,” Emnlp, no. October, pp. 289–299, 2013.
[7] A. Rahman and V. Ng, “Coreference Resolution with World Knowledge,” Acl, no. June, pp. 814–824, 2011.
[8] L. Ratinov and D. Roth, “Learning-based multi-sieve co-reference resolution with knowledge,” Proc. 2012 Jt. Conf. Empir. Methods Nat. Lang. Process. Comput. Nat. Lang. Learn., no. 1, pp. 1234–1244, 2012.
[9] E. Bengtson and D. Roth, “Understanding the value of features for coreference resolution,” Proc. Conf. Empir. Methods Nat. Lang. Process. - EMNLP ’08, vol. 51, no. October, p. 294, 2008.
[10] D. Bean and E. Riloff, “Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution,” Proc. Hum. Lang. Technol. Conf. North Am. Chapter Assoc. Comput. Linguist. (HLT-NAACL 2004), pp. 297–304, 2004.
[11] S. Huang, Y. Zhang, J. Zhou, and J. Chen, “Coreference Resolution using Markov Logic Network,” Science (80-. )., pp. 157–168, 2009.
[12] F. Chen, “Coreference Resolution with Markov Logic,” Assoc. Adv. Artif. Intell., 2009.
[13] Y. Song, J. Jiang, W. X. Zhao, S. Li, H. Wang, and 王厚峰, “Joint learning for coreference resolution with Markov logic,” Proc. 2012 Jt. Conf. Empir. Methods Nat. Lang. Process. Comput. Nat. Lang. Learn., no. July, pp. 1245–1254, 2012.
[14] T. Bögel and A. Frank, “A joint inference architecture for global coreference clustering with anaphoricity,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 8105 LNAI, pp. 35–46, 2013.
[15] H. Poon and P. Domingos, “Joint Unsupervised Coreference Resolution with Markov logic,” Proc. Conf. Empir. Methods Nat. Lang. Process., no. October, p. 650, 2008.
[16] H. Lee, Y. Peirsman, A. Chang, N. Chambers, M. Surdeanu, and D. Jurafsky, “Stanford ’ s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task,” Proc. Fifteenth Conf. Comput. Nat. Lang. Learn. Shar. Task. Assoc. Comput. Linguist., pp. 28–34, 2011.
[17] M. Richardson and P. Domingos, “Markov logic networks,” Mach. Learn., vol. 62, no. 1–2 SPEC. ISS., pp. 107–136, 2006.
[18] T. Chklovski and P. Pantel, “VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations.,” EMNLP, no. Lin 1997, 2004.
[19] G. A. Miller, “WordNet: a lexical database for English,” Commun. ACM 38.11 39-41., 1995.
[20] M. Baroni and A. Lenci, “Distributional Memory: A General Framework for Corpus-Based Semantics,” Comput. Linguist., vol. 36, no. 4, pp. 673–721, 2010.
[21] B. Comrie, “The syntax of action nominals: A cross-language study,” Lingua, vol. 40, no. 2–3, pp. 177–201, 1976.
[22] et al Pustejovsky, James, “The timebank corpus,” Corpus Linguist., pp. 647–656, 2003.
[23] R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa, “Natural Language Processing (almost) from Scratch,” J. Mach. Learn. Res., vol. 12, pp. 2493–2537, 2011.
[24] S. University, “Stanford CoreNLP.” .
[25] M. Ciaramita and Y. Altun, “Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger,” Proc. 2006 Conf. Empir. Methods Nat. Lang. Process. - EMNLP ’06, no. July, pp. 594–602, 2006.
[26] M. Richardson and P. Domingos, “Markov logic networks,” Mach. Learn., vol. 62, no. 1–2, pp. 107–136, 2006.
[27] F. Niu, C. Ré, A. Doan, and J. Shavlik, “Tuffy: Scaling up Statistical Inference in Markov Logic Networks using an RDBMS,” Proc. VLDB Endow., vol. 4, no. 6, pp. 373–384, 2011.
[28] M. Vilain, J. Burger, J. Aberdeen, D. Connolly, and L. Hirschman, “A Model-Theoretic Coreference Scoring Scheme,” Messag. Underst. Conf., no. 1, pp. 45–52, 1995.
[29] A. Bagga and B. Baldwin, “Algorithms for scoring coreference chains,” in The First International Con-ference on Language Resources and Evaluation Work-shop on Linguistics Coreference, 1998, pp. 563–566.
[30] Marta Recasens and Eduard Hovy, “BLANC: Implementing the Rand index for coreference evaluation,” Nat. Lang. Eng., vol. 17(4), pp. 485–510, 2011.
[31] W. M. Rand, “Objective criteria for the evaluation of clustering methods,” J. Am. Stat. Assoc., vol. 66(336), pp. 846–850, 1971.
