Template kernels for dependency parsing

Hillel Taub-Tabib, Yoav Goldberg, Amir Globerson

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

Abstract

A common approach to dependency parsing is scoring a parse via a linear function of a set of indicator features. These features are typically manually constructed from templates that are applied to parts of the parse tree. The templates define which properties of a part should combine to create features. Existing approaches consider only a small subset of the possible combinations, due to statistical and computational efficiency considerations. In this work we present a novel kernel which facilitates efficient parsing with feature representations corresponding to a much larger set of combinations. We integrate the kernel into a parse reranking system and demonstrate its effectiveness on four languages from the CoNLL-X shared task.1

Original languageEnglish
Title of host publicationNAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1422-1427
Number of pages6
ISBN (Electronic)9781941643495
DOIs
StatePublished - 2015
Externally publishedYes
EventConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 - Denver, United States
Duration: 31 May 20155 Jun 2015

Publication series

NameNAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

ConferenceConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
Country/TerritoryUnited States
CityDenver
Period31/05/155/06/15

Fingerprint

Dive into the research topics of 'Template kernels for dependency parsing'. Together they form a unique fingerprint.

Cite this