Learning reliability of parses for domain adaptation of dependency parsing

Daisuke Kawahara, Kiyotaka Uchimoto

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

22 Citations (Scopus)

Abstract

The accuracy of parsing has exceeded 90% recently, but this is not high enough to use parsing results practically in natural language processing (NLP) applications such as paraphrase acquisition and relation extraction. We present a method for detecting reliable parses out of the outputs of a single dependency parser. This technique is also applied to domain adaptation of dependency parsing. Our goal was to improve the performance of a state-of-the-art dependency parser on the data set of the domain adaptation track of the CoNLL 2007 shared task, a formidable challenge.

Original languageEnglish
Title of host publicationIJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages709-714
Number of pages6
ISBN (Electronic)9780000000002
Publication statusPublished - 2008
Event3rd International Joint Conference on Natural Language Processing, IJCNLP 2008 - Hyderabad, India
Duration: 2008 Jan 72008 Jan 12

Publication series

NameIJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference
Volume2

Conference

Conference3rd International Joint Conference on Natural Language Processing, IJCNLP 2008
Country/TerritoryIndia
CityHyderabad
Period08/1/708/1/12

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Learning reliability of parses for domain adaptation of dependency parsing'. Together they form a unique fingerprint.

Cite this