A pipeline approach for syntactic and semantic dependency parsing

Yotaro Watanabe, Masakazu Iwatate, Masayuki Asahara, Yuji Matsumoto

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

2 Citations (Scopus)

Abstract

This paper describes our system for syntactic and semantic dependency parsing to participate the shared task of CoNLL-2008. We use a pipeline approach, in which syntactic dependency parsing, word sense disambiguation, and semantic role labeling are performed separately: Syntactic dependency parsing is performed by a tournament model with a support vector machine; word sense disambiguation is performed by a nearest neighbour method in a compressed feature space by probabilistic latent semantic indexing; and semantic role labeling is performed by a an online passive-aggressive algorithm. The submitted result was 79.10 macroaverage F1 for the joint task, 87.18% syntactic dependencies LAS, and 70.84 semantic dependencies F1. After the deadline, we constructed the other configuration, which achieved 80.89 F1 for the joint task, and 74.53 semantic dependencies F1. The result shows that the configuration of pipeline is a crucial issue in the task.

Original languageEnglish
Title of host publicationCoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
PublisherAssociation for Computational Linguistics (ACL)
Pages228-232
Number of pages5
ISBN (Print)1905593481, 9781905593484
DOIs
Publication statusPublished - 2008
Event12th Conference on Computational Natural Language Learning, CoNLL 2008 - Manchester, United Kingdom
Duration: 2008 Aug 162008 Aug 17

Publication series

NameCoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning

Other

Other12th Conference on Computational Natural Language Learning, CoNLL 2008
CountryUnited Kingdom
CityManchester
Period08/8/1608/8/17

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Fingerprint Dive into the research topics of 'A pipeline approach for syntactic and semantic dependency parsing'. Together they form a unique fingerprint.

Cite this