Skip to main navigation Skip to search Skip to main content

Finding arguments as sequence labeling in discourse parsing

  • Ziwei Fan
  • , Zhenghua Li*
  • , Min Zhang
  • *Corresponding author for this work

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

Abstract

This paper describes our system for the CoNLL-2016 Shared Task on Shallow Discourse Parsing on English. We adopt a cascaded framework consisting of nine components, among which six are casted as sequence labeling tasks and the remaining three are treated as classification problems. All our sequence labeling and classification models are implemented based on linear models with averaged perceptron training. Our feature sets are mostly borrowed from previous works. The main focus of our effort is to recall cases when Arg1 locates at sentences far before the connective phrase, with some yet limited success.

Original languageEnglish
Title of host publicationProceedings of the 20th SIGNLL Conference on Computational Natural Language Learning
Subtitle of host publicationShared Task, CoNLL 2016
PublisherAssociation for Computational Linguistics (ACL)
Pages150-157
Number of pages8
ISBN (Electronic)1932432663, 9781932432664
DOIs
StatePublished - 2016
Externally publishedYes
Event20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016 - Berlin, Germany
Duration: 7 Aug 201612 Aug 2016

Publication series

NameProceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

Conference

Conference20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016
Country/TerritoryGermany
CityBerlin
Period7/08/1612/08/16

Fingerprint

Dive into the research topics of 'Finding arguments as sequence labeling in discourse parsing'. Together they form a unique fingerprint.

Cite this