Encoding Semantic Resources in Syntactic Structures for Passage Reranking

In this paper, we propose to use semantic knowledge from Wikipedia and largescale structured knowledge datasets available as Linked Open Data (LOD) for the answer passage reranking task. We represent question and candidate answer passages with pairs of shallow syntactic/semantic trees, whose constituents are connected using LOD. The trees are processed by SVMs and tree kernels, which can automatically exploit tree fragments. The experiments with our SVM rank algorithm on the TREC Question Answering (QA) corpus show that the added relational information highly improves over the state of the art, e.g., about 15.4% of relative improvement in P@1.

[1]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[2]  Alessandro Moschitti,et al.  Structural relationships for large-scale learning of answer re-ranking , 2012, SIGIR '12.

[3]  Jens Lehmann,et al.  DBpedia - A crystallization point for the Web of Data , 2009, J. Web Semant..

[4]  Rada Mihalcea,et al.  Linking Documents to Encyclopedic Knowledge , 2008, IEEE Intelligent Systems.

[5]  Ian H. Witten,et al.  An open-source toolkit for mining Wikipedia , 2013, Artif. Intell..

[6]  Jennifer Chu-Carroll,et al.  Building Watson: An Overview of the DeepQA Project , 2010, AI Mag..

[7]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

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

[9]  Jaime G. Carbonell,et al.  Rank learning for factoid question answering with linguistic and semantic constraints , 2010, CIKM.

[10]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[11]  Aditya Kalyanpur,et al.  Leveraging Community-Built Knowledge for Type Coercion in Question Answering , 2011, International Semantic Web Conference.

[12]  Ellen M. Voorhees,et al.  Overview of the TREC 2004 Novelty Track. , 2005 .

[13]  Alessandro Moschitti,et al.  Automatic Feature Engineering for Answer Selection and Extraction , 2013, EMNLP.

[14]  Aditya Kalyanpur,et al.  Typing candidate answers using type coercion , 2012, IBM J. Res. Dev..

[15]  Alessandro Moschitti,et al.  Kernels on Linguistic Structures for Answer Extraction , 2008, ACL.

[16]  Alessandro Moschitti,et al.  Building structures from classifiers for passage reranking , 2013, CIKM.

[17]  Alessandro Moschitti,et al.  Syntactic and Semantic Kernels for Short Text Pair Categorization , 2009, EACL.

[18]  Roberto Basili,et al.  Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification , 2007, ACL.

[19]  Alessandro Moschitti,et al.  Learning Adaptable Patterns for Passage Reranking , 2013, CoNLL.