Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification

A. Moschitti; S. Quarteroni; R. Basili; S. Manandhar

Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification

A. Moschitti, S. Quarteroni, R. Basili, S. Manandhar

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We study the impact of syntactic and shallow semantic information in automatic classifi- cation of questions and answers and answer re-ranking. We define (a) new tree struc- tures 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 ex- periments suggest that syntactic information helps tasks such as question/answer classifi- cation and that shallow semantics gives re- markable contribution when a reliable set of PASs can be extracted, e.g. from answers.

Original language	English
Title of host publication	Proceedings of 45th Annual meeting of the Association for Computational Linguistics
Pages	776-783
Number of pages	7
Publication status	Published - 2007
Event	ACL 2007 - Prague, Czech Republic Duration: 23 Jun 2007 → 30 Jun 2007

Conference

Conference	ACL 2007
City	Prague, Czech Republic
Period	23/06/07 → 30/06/07

Access to Document

http://www.aclweb.org/anthology-new/P/P07/P07-1098.pdf

Cite this

@inproceedings{866af630eaa34302a331901f85ed2bd1,

title = "Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification",

abstract = "We study the impact of syntactic and shallow semantic information in automatic classifi- cation of questions and answers and answer re-ranking. We define (a) new tree struc- tures 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 ex- periments suggest that syntactic information helps tasks such as question/answer classifi- cation and that shallow semantics gives re- markable contribution when a reliable set of PASs can be extracted, e.g. from answers.",

author = "A. Moschitti and S. Quarteroni and R. Basili and S. Manandhar",

year = "2007",

language = "English",

pages = "776--783",

booktitle = "Proceedings of 45th Annual meeting of the Association for Computational Linguistics",

note = "ACL 2007 ; Conference date: 23-06-2007 Through 30-06-2007",

}

TY - GEN

T1 - Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification

AU - Moschitti, A.

AU - Quarteroni, S.

AU - Basili, R.

AU - Manandhar, S.

PY - 2007

Y1 - 2007

N2 - We study the impact of syntactic and shallow semantic information in automatic classifi- cation of questions and answers and answer re-ranking. We define (a) new tree struc- tures 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 ex- periments suggest that syntactic information helps tasks such as question/answer classifi- cation and that shallow semantics gives re- markable contribution when a reliable set of PASs can be extracted, e.g. from answers.

AB - We study the impact of syntactic and shallow semantic information in automatic classifi- cation of questions and answers and answer re-ranking. We define (a) new tree struc- tures 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 ex- periments suggest that syntactic information helps tasks such as question/answer classifi- cation and that shallow semantics gives re- markable contribution when a reliable set of PASs can be extracted, e.g. from answers.

M3 - Conference contribution

SP - 776

EP - 783

BT - Proceedings of 45th Annual meeting of the Association for Computational Linguistics

T2 - ACL 2007

Y2 - 23 June 2007 through 30 June 2007

ER -