Skip to main navigation Skip to search Skip to main content

LINGMESS: Linguistically Informed Multi Expert Scorers for Coreference Resolution

  • Shon Otmazgin
  • , Arie Cattan
  • , Yoav Goldberg

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

30 Scopus citations

Abstract

Current state-of-the-art coreference systems are based on a single pairwise scoring component, which assigns to each pair of mention spans a score reflecting their tendency to core-fer to each other. We observe that different kinds of mention pairs require different information sources to assess their score. We present LINGMESS, a linguistically motivated categorization of mention-pairs into 6 types of coreference decisions and learn a dedicated trainable scoring function for each category. This significantly improves the accuracy of the pairwise scorer as well as of the overall coreference performance on the English Ontonotes coreference corpus and 5 additional datasets.

Original languageEnglish
Title of host publicationEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages2744-2752
Number of pages9
ISBN (Electronic)9781959429449
DOIs
StatePublished - 1 Jan 2023
Externally publishedYes
Event17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Dubrovnik, Croatia, Croatia
Duration: 2 May 20236 May 2023

Publication series

NameEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023
Country/TerritoryCroatia
CityDubrovnik, Croatia
Period2/05/236/05/23

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'LINGMESS: Linguistically Informed Multi Expert Scorers for Coreference Resolution'. Together they form a unique fingerprint.

Cite this