Discourse processing for context question answering based on linguistic knowledge

Motivated by the recent effort on scenario-based context question answering (QA), this paper investigates the role of discourse processing and its implication on query expansion for a sequence of questions. Our view is that a question sequence is not random, but rather follows a coherent manner to serve some information goals. Therefore, this sequence of questions can be considered as a mini discourse with some characteristics of discourse cohesion. Understanding such a discourse will help QA systems better interpret questions and retrieve answers. Thus, we examine three models driven by Centering Theory for discourse processing: a reference model that resolves pronoun references for each question, a forward model that makes use of the forward looking centers from previous questions, and a transition model that takes into account the transition state between adjacent questions. Our empirical results indicate that more sophisticated processing based on discourse transitions and centers can significantly improve the performance of document retrieval compared to models that only resolve references. This paper provides a systematic evaluation of these models and discusses their potentials and limitations in processing coherent context questions.

[1]  Marilyn A. Walker,et al.  Japanese Discourse and the Process of Centering , 1994, Comput. Linguistics.

[2]  Carl Pollard,et al.  A Centering Approach to Pronouns , 1987, ACL.

[3]  Elizabeth D. Liddy,et al.  Context-based question-answering evaluation , 2004, SIGIR '04.

[4]  Sanda M. Harabagiu,et al.  LCC Tools for Question Answering , 2002, TREC.

[5]  Barbara J. Grosz,et al.  Focusing and Description in Natural Language Dialogues , 1979 .

[6]  Richard F. E. Sutcliffe,et al.  Question Answering Using the DLT System at TREC 2002 , 2002, TREC.

[7]  Scott Weinstein,et al.  Centering: A Framework for Modeling the Local Coherence of Discourse , 1995, CL.

[8]  Candace L. Sidner,et al.  Attention, Intentions, and the Structure of Discourse , 1986, CL.

[9]  Udo Hahn,et al.  Functional Centering , 1996, ACL.

[10]  Malvina Nissim,et al.  Question Answering with QED at TREC 2005 , 2005, TREC.

[11]  Tomek Strzalkowski,et al.  ILQUA--An IE-Driven Question Answering System , 2005, TREC.

[12]  Marilyn A. Walker,et al.  Evaluating Discourse Processing Algorithms , 1989, ACL.

[13]  Scott Weinstein,et al.  Control of Inference: Role of Some Aspects of Discourse Structure-Centering , 1981, IJCAI.

[14]  William C. Mann,et al.  RHETORICAL STRUCTURE THEORY: A THEORY OF TEXT ORGANIZATION , 1987 .

[15]  Jon Doyle,et al.  DalTREC 2005 QA System Jellyfish: Mark-and-Match Approach to Question Answering , 2005, TREC.

[16]  M. Walker,et al.  Centering Theory in Discourse , 1998 .

[17]  Aravind K. Joshi,et al.  Centered Logic: The Role of Entity Centered Sentence Representation in Natural Language Inferencing , 1979, IJCAI.

[18]  Andrew Kehler,et al.  The Effect of Establishing Coherence in Ellipsis and Anaphora Resolution , 1993, ACL.

[19]  Sanda M. Harabagiu,et al.  Experiments with Interactive Question-Answering , 2005, ACL.

[20]  Scott Weinstein,et al.  Providing a Unified Account of Definite Noun Phrases in Discourse , 1983, ACL.

[21]  B. Webber,et al.  Elements of Discourse Understanding , 1983 .

[22]  Tomek Strzalkowski,et al.  From Discourse to Logic , 1991 .

[23]  Robert J. Gaizauskas,et al.  Evaluating Passage Retrieval Approaches for Question Answering , 2004, ECIR.

[24]  Horacio Saggion,et al.  The University of Sheffield's TREC 2003 Q&A Experiments , 2003, TREC.

[25]  Barbara J. Grosz,et al.  The representation and use of focus in dialogue understanding. , 1977 .

[26]  J. Hobbs.  On the coherence and structure of discourse , 1985 .

[27]  Jeanette K. Gundel.  The Role of Topic and Comment in Linguistic Theory , 1988 .

[28]  Michael Halliday,et al.  Cohesion in English , 1976 .

[29]  Maarten de Rijke,et al.  Language Modeling Approaches for Enterprise Tasks , 2005, TREC.

[30]  N. Cocchiarella,et al.  Situations and Attitudes. , 1986 .

[31]  Candace L. Sidner,et al.  Towards a computational theory of definite anaphora comprehension in English discourse , 1979 .

[32]  Mirella Lapata,et al.  Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05) , 2005, ACL 2005.

[33]  M. Walker,et al.  Centering in Naturally-Occurring Discourse: An Overview , 2007 .

[34]  Karen Kukich,et al.  Evaluation of text coherence for electronic essay scoring systems , 2004, Natural Language Engineering.

[35]  James H. Martin,et al.  Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition , 2000, Prentice Hall series in artificial intelligence.

[36]  Laurence R. Horn,et al.  The handbook of pragmatics , 2004 .

[37]  Brad Abbott,et al.  Definiteness and Indefiniteness , 2008 .

[38]  Mihai Surdeanu,et al.  TALP-UPC at TREC 2005: Experiments Using a Voting Scheme Among Three Heterogeneous QA Systems , 2005, TREC.

[39]  Sanda M. Harabagiu,et al.  Answering Complex, List and Context Questions with LCC's Question-Answering Server , 2001, TREC.

[40]  Megumi Kameyama,et al.  A Property-Sharing Constraint in Centering , 1986, ACL.

[41]  Tomek Strzalkowski,et al.  HITIQA: An Interactive Question Answering System: A Preliminary Report , 2003, ACL 2003.