Improving a strong neural parser with conjunction-specific features

Jessica Ficler, Yoav Goldberg

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

Abstract

While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.

Original languageEnglish
Title of host publicationShort Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages343-348
Number of pages6
ISBN (Electronic)9781510838604
DOIs
StatePublished - 2017
Event15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain
Duration: 3 Apr 20177 Apr 2017

Publication series

Name15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
Volume2

Conference

Conference15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Country/TerritorySpain
CityValencia
Period3/04/177/04/17

All Science Journal Classification (ASJC) codes

  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Improving a strong neural parser with conjunction-specific features'. Together they form a unique fingerprint.

Cite this