Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification

We study the impact of syntactic and shallow semantic information in automatic classification of questions and answers and answer re-ranking. We define (a) new tree structures based on shallow semantics encoded in Predicate Argument Structures (PASs) and (b) new kernel functions to exploit the representational power of such structures with Support Vector Machines. Our experiments suggest that syntactic information helps tasks such as question/answer classification and that shallow semantics gives remarkable contribution when a reliable set of PASs can be extracted, e.g. from answers.

[1]  S. Manandhar,et al.  User Modelling for Adaptive Question Answering and Information Retrieval , 2006 .

[2]  Ellen M. Voorhees,et al.  Overview of TREC 2001 , 2001, TREC.

[3]  Djoerd Hiemstra,et al.  Challenges in information retrieval and language modeling: report of a workshop held at the center for intelligent information retrieval, University of Massachusetts Amherst, September 2002 , 2003, SIGF.

[4]  Suresh Manandhar,et al.  User Modeling for Adaptive Question Answering and Information Retrieval , 2006, FLAIRS.

[5]  Martha Palmer,et al.  From TreeBank to PropBank , 2002, LREC.

[6]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[7]  Dell Zhang,et al.  Question classification using support vector machines , 2003, SIGIR.

[8]  Dan Roth,et al.  Learning question classifiers: the role of semantic information , 2005, Natural Language Engineering.

[9]  Tat-Seng Chua,et al.  Generic soft pattern models for definitional question answering , 2005, SIGIR '05.

[10]  Dmitry Zelenko,et al.  Kernel Methods for Relation Extraction , 2002, J. Mach. Learn. Res..

[11]  Eisaku Maeda,et al.  NTT Question Answering System in TREC 2001 , 2001, TREC.

[12]  Roberto Basili,et al.  Hierarchical Semantic Role Labeling , 2005, CoNLL.

[13]  Charles L. A. Clarke,et al.  The effect of document retrieval quality on factoid question answering performance , 2004, Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.

[14]  Michael Collins,et al.  New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron , 2002, ACL.

[15]  Oren Etzioni,et al.  Scaling question answering to the Web , 2001, WWW '01.

[16]  Ming Zhou,et al.  Reranking Answers for Definitional QA Using Language Modeling , 2006, ACL.

[17]  Alessandro Moschitti,et al.  Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees , 2006, ECML.