Abstract：Interactive Question Answering (IQA), a hot research topic in the area of QA, can interact with users to process a series of questions from users just like talking to them. This paper systematically explores anaphoricity determination for coreference resolution in IQA. The statistic of the corpus shows the distribution of anaphoricity and the experiment in the TREC QA questions set which uses the rule-based and flat feature-based method shows the performance of anaphoricity determination for coreference resolution in IQA. On the basis of the characteristic of IQA, two flat features about proper noun are proposed. Experimental results show that the proper method and the proposed feature is effective.
[1] Nick Webb. Introduction of Interactive Question Answering Workshop[C]//Proceedings of the Interactive Question Answering Workshop at HLT-NAACL 2006, 2006. [2] Ellen M Voorhees. Overview of the TREC 2004 Question Answering Track. http://trec.nist.gov/, 2004. [3] Ng V, Cardie C. Identify anaphoric and non-anaphoric noun phrases to improve coreferecne resolution[C]//Proceedings of the 19th Int Conf on Computational Linguistics (COLING), 2002:976-984. [4] Soon W M, Ng H T, Lim D. A machine learning approach of coreference resolution of noun phrase[J]. Computational Linguistics, 2001, 27(4): 521-544. [5] Chai J, Jin R. Discourse structure for context question answering[C]//Proceedings of HLT-NAACL 2004 Workshop on Pragmatics of Question Answering, 2004:23-30. [6] Carbonell J G. Discourse pragmatics and ellipsis resolution in task-oriented natural language interfaces[C]//Proceedings of 21st Annual Meeting on Association for Computational Linguistics, 1983:164-168. [7] Nils D, Jonsson A. Empirical studies of discourse representations for natural language interfaces[C]//Proceedings of 4th Conference of the European Chapter of the ACL, 1989:291-298. [8] Dongsheng Wang. Answering contextual questions based on ontologies and question templates[J]. Frontiers of Computer Science in China, 2011, 5(4): 405-418. [9] Joyce Y Chai, Rong Jing. Discourse structure for context question answering[C]//Proceedings of the Workshop on Pragmatics of Question Answering at HLT-NAACL, 2004:23-30. [10] Lappin S, Herbert J L. An algorithm for pronominal anaphora resolution [J]. Computational Linguistic, 1994, 20(4):535-561.[11] Bean D, Riloff E. Corpus-based identification of non-anaphoric noun phrases[C]//Proceedings of the 27th Annual Meeting of the Association for Computational Linguistics (ACL), 1999:373-380. [12] Evans R. Applying Machine Learning Toward an Automatic Classification of It[J]. Literary and Linguistic Computing, 2011,16(1):45-57. [13] Müller C. Automatic detection of non-referential It in spoken multi-party dialog[C]//Proceedings of the EACL, 2006,49-56. [14] Zhou G D, Kong F. Global learning of noun phrase anaphoricity in coreference resolution via label propagation [C]//Proceedings of the 2009 Conf on Empirical Methods in Natural Language Processing, 2009:978-986. [15] 孔芳,朱巧明,周国栋. 中英文指代消解中待消解项识别的研究[J]. 计算机研究与发展, 2012, 49(5):1072-1085. [16] Poesio M, Vieira R. A corpus-based investigation of definite description use[J]. Computational Linguistics, 1998:183-216.
2014, Vol. 28 
