Making tree kernels practical for natural language learning

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

176 Citations (Scopus)

Abstract

In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (b) a lower accuracy than traditional attribute/value methods. In this paper, we show that tree kernels are very helpful in the processing of natural language as (a) we provide a simple algorithm to compute tree kernels in linear average running time and (b) our study on the classification properties of diverse tree kernels show that kernel combinations always improve the traditional methods. Experiments with Support Vector Machines on the predicate argument classification task provide empirical support to our thesis.

Original languageEnglish
Title of host publicationEACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Pages113-120
Number of pages8
Publication statusPublished - 1 Dec 2006
Externally publishedYes
Event11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006 - Trento, Italy
Duration: 3 Apr 20067 Apr 2006

Other

Other11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006
CountryItaly
CityTrento
Period3/4/067/4/06

Fingerprint

language
learning
experiment
Values
Kernel
Language Acquisition
Natural Language
time
Support Vector Machine
Experiment

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Moschitti, A. (2006). Making tree kernels practical for natural language learning. In EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 113-120)

Making tree kernels practical for natural language learning. / Moschitti, Alessandro.

EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. 2006. p. 113-120.

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

Moschitti, A 2006, Making tree kernels practical for natural language learning. in EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. pp. 113-120, 11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006, Trento, Italy, 3/4/06.
Moschitti A. Making tree kernels practical for natural language learning. In EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. 2006. p. 113-120
Moschitti, Alessandro. / Making tree kernels practical for natural language learning. EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. 2006. pp. 113-120
@inproceedings{e16b314bac0a41b594d79da02153be13,
title = "Making tree kernels practical for natural language learning",
abstract = "In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (b) a lower accuracy than traditional attribute/value methods. In this paper, we show that tree kernels are very helpful in the processing of natural language as (a) we provide a simple algorithm to compute tree kernels in linear average running time and (b) our study on the classification properties of diverse tree kernels show that kernel combinations always improve the traditional methods. Experiments with Support Vector Machines on the predicate argument classification task provide empirical support to our thesis.",
author = "Alessandro Moschitti",
year = "2006",
month = "12",
day = "1",
language = "English",
isbn = "1932432590",
pages = "113--120",
booktitle = "EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Making tree kernels practical for natural language learning

AU - Moschitti, Alessandro

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (b) a lower accuracy than traditional attribute/value methods. In this paper, we show that tree kernels are very helpful in the processing of natural language as (a) we provide a simple algorithm to compute tree kernels in linear average running time and (b) our study on the classification properties of diverse tree kernels show that kernel combinations always improve the traditional methods. Experiments with Support Vector Machines on the predicate argument classification task provide empirical support to our thesis.

AB - In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (b) a lower accuracy than traditional attribute/value methods. In this paper, we show that tree kernels are very helpful in the processing of natural language as (a) we provide a simple algorithm to compute tree kernels in linear average running time and (b) our study on the classification properties of diverse tree kernels show that kernel combinations always improve the traditional methods. Experiments with Support Vector Machines on the predicate argument classification task provide empirical support to our thesis.

UR - http://www.scopus.com/inward/record.url?scp=84874714333&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874714333&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874714333

SN - 1932432590

SN - 9781932432596

SP - 113

EP - 120

BT - EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

ER -