Syntactic and semantic kernels for short text pair categorization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)

Abstract

Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy.

Original languageEnglish
Title of host publicationEACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings
Pages576-584
Number of pages9
Publication statusPublished - 1 Dec 2009
Externally publishedYes
Event12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009 - Athens, Greece
Duration: 30 Mar 20093 Apr 2009

Other

Other12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009
CountryGreece
CityAthens
Period30/3/093/4/09

Fingerprint

semantics
learning method
syntax
exploitation
experiment
language
Syntax
Kernel
Kernel Methods
Support Vector Machine
Exploitation
Experiment
Semantic Structure
Language Model
Semantic Information
Bag

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Moschitti, A. (2009). Syntactic and semantic kernels for short text pair categorization. In EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings (pp. 576-584)

Syntactic and semantic kernels for short text pair categorization. / Moschitti, Alessandro.

EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. 2009. p. 576-584.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Moschitti, A 2009, Syntactic and semantic kernels for short text pair categorization. in EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. pp. 576-584, 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009, Athens, Greece, 30/3/09.
Moschitti A. Syntactic and semantic kernels for short text pair categorization. In EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. 2009. p. 576-584
Moschitti, Alessandro. / Syntactic and semantic kernels for short text pair categorization. EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. 2009. pp. 576-584
@inproceedings{6e3d477568b4447d8c2fdcf1b106550b,
title = "Syntactic and semantic kernels for short text pair categorization",
abstract = "Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy.",
author = "Alessandro Moschitti",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781932432169",
pages = "576--584",
booktitle = "EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings",

}

TY - GEN

T1 - Syntactic and semantic kernels for short text pair categorization

AU - Moschitti, Alessandro

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy.

AB - Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84891604874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891604874&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84891604874

SN - 9781932432169

SP - 576

EP - 584

BT - EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings

ER -