A practical perspective on latent structured prediction for coreference resolution

Iryna Haponchyk, Alessandro Moschitti

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

5 Citations (Scopus)

Abstract

Latent structured prediction theory proposes powerful methods such as Latent Structural SVM (LSSVM), which can potentially be very appealing for coreference resolution (CR). In contrast, only small work is available, mainly targeting the latent structured perceptron (LSP). In this paper, we carried out a practical study comparing for the first time online learning with LSSVM. We analyze the intricacies that may have made initial attempts to use LSSVM fail, i.e., a huge training time and much lower accuracy produced by Kruskal's spanning tree algorithm. In this respect, we also propose a new effective feature selection approach for improving system efficiency. The results show that LSP, if correctly parameterized, produces the same performance as LSSVM, being at the same time much more efficient.

Original languageEnglish
Title of host publicationShort Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages143-149
Number of pages7
Volume2
ISBN (Electronic)9781510838604
Publication statusPublished - 1 Jan 2017
Event15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain
Duration: 3 Apr 20177 Apr 2017

Other

Other15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
CountrySpain
CityValencia
Period3/4/177/4/17

    Fingerprint

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics

Cite this

Haponchyk, I., & Moschitti, A. (2017). A practical perspective on latent structured prediction for coreference resolution. In Short Papers (Vol. 2, pp. 143-149). Association for Computational Linguistics (ACL).