Skip to main navigation Skip to search Skip to main content

Convolution kernel over packed parse forest

  • Agency for Science, Technology and Research, Singapore

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a convolution forest kernel to effectively explore rich structured features embedded in a packed parse forest. As opposed to the convolution tree kernel, the proposed forest kernel does not have to commit to a single best parse tree, is thus able to explore very large object spaces and much more structured features embedded in a forest. This makes the proposed kernel more robust against parsing errors and data sparseness issues than the convolution tree kernel. The paper presents the formal definition of convolution forest kernel and also illustrates the computing algorithm to fast compute the proposed convolution forest kernel. Experimental results on two NLP applications, relation extraction and semantic role labeling, show that the proposed forest kernel significantly outperforms the baseline of the convolution tree kernel.

Original languageEnglish
Title of host publicationACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings
EditorsJan Hajic, Sandra Carberry, Stephen Clark
PublisherAssociation for Computational Linguistics (ACL)
Pages875-885
Number of pages11
ISBN (Electronic)1932432663, 9781932432664
StatePublished - 2010
Externally publishedYes
Event48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden
Duration: 11 Jul 201016 Jul 2010

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume2010-July
ISSN (Print)0736-587X

Conference

Conference48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
Country/TerritorySweden
CityUppsala
Period11/07/1016/07/10

Fingerprint

Dive into the research topics of 'Convolution kernel over packed parse forest'. Together they form a unique fingerprint.

Cite this