Discourse Complements Lexical Semantics for Non-factoid Answer Reranking

We propose a robust answer reranking model for non-factoid questions that integrates lexical semantics with discourse information, driven by two representations of discourse: a shallow representation centered around discourse markers, and a deep one based on Rhetorical Structure Theory. We evaluate the proposed model on two corpora from different genres and domains: one from Yahoo! Answers and one from the biology domain, and two types of non-factoid questions: manner and reason. We experimentally demonstrate that the discourse structure of nonfactoid answers provides information that is complementary to lexical semantic similarity between question and answer, improving performance up to 24% (relative) over a state-of-the-art model that exploits lexical semantic similarity alone. We further demonstrate excellent domain transfer of discourse information, suggesting these discourse features have general utility to non-factoid question answering.

[1]  Jong-Hoon Oh,et al.  Why-Question Answering using Intra- and Inter-Sentential Causal Relations , 2013, ACL.

[2]  Dragomir R. Radev,et al.  Question-answering by predictive annotation , 2000, SIGIR '00.

[3]  G. Meade.  Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory , 2001 .

[4]  Graeme Hirst,et al.  Text-level Discourse Parsing with Rich Linguistic Features , 2012, ACL.

[5]  Suzan Verberne,et al.  What Is Not in the Bag of Words for Why-QA? , 2010, CL.

[6]  Hans van Halteren,et al.  Learning to rank for why-question answering , 2011, Information Retrieval.

[7]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[8]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[9]  Lou Boves,et al.  Discourse-based answering of why-questions , 2006, Trait. Autom. des Langues.

[10]  Ming-Wei Chang,et al.  Question Answering Using Enhanced Lexical Semantic Models , 2013, ACL.

[11]  Pedro M. Domingos.  A few useful things to know about machine learning , 2012, Commun. ACM.

[12]  Dan Feng,et al.  Ranking community answers by modeling question-answer relationships via analogical reasoning , 2009, SIGIR.

[13]  Mihai Surdeanu,et al.  Learning to Rank Answers to Non-Factoid Questions from Web Collections , 2011, CL.

[14]  Daniel Marcu,et al.  The rhetorical parsing, summarization, and generation of natural language texts , 1998 .

[15]  Klaus Nordhausen,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman , 2009 .

[16]  Olga Vechtomova,et al.  Book Review: Introduction to Information Retrieval by Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze , 2009, CL.

[17]  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.

[18]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

[19]  Ryuichiro Higashinaka,et al.  Corpus-based Question Answering for why-Questions , 2008, IJCNLP.

[20]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[21]  Yi Liu,et al.  Statistical Machine Translation for Query Expansion in Answer Retrieval , 2007, ACL.

[22]  Sanda Harabagiu,et al.  High-performance, open-domain question answering from large text collections , 2001 .