Webbläsaren som du använder stöds inte av denna webbplats. Alla versioner av Internet Explorer stöds inte längre, av oss eller Microsoft (läs mer här: * https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Var god och använd en modern webbläsare för att ta del av denna webbplats, som t.ex. nyaste versioner av Edge, Chrome, Firefox eller Safari osv.

Default user image.

Anders Björkelund

Forskare

Default user image.

Exploring Lexicalized Features for Coreference Resolution

Författare

  • Anders Björkelund
  • Pierre Nugues

Summary, in English

In this paper, we describe a coreference solver based on the extensive use of lexical features and features extracted from dependency graphs of the sentences. The solver uses Soon et al. (2001)'s classical resolution algorithm based on a pairwise classification of the mentions.



We applied this solver to the closed track of the CoNLL 2011 shared task (Pradhan et al., 2011). We carried out a systematic optimization of the feature set using cross-validation that led us to retain 24 features. Using this set, we reached a MUC score of 58.61 on the test set of the shared task. We analyzed the impact of the features on the development set and we show the importance of lexicalization as well as of properties related to dependency links in coreference resolution.

Avdelning/ar

  • ELLIIT: the Linköping-Lund initiative on IT and mobile communication
  • Institutionen för datavetenskap
  • Robotik och Semantiska System

Publiceringsår

2011

Språk

Engelska

Sidor

45-50

Publikation/Tidskrift/Serie

CoNLL 2011 - 15th Conference on Computational Natural Language Learning: Shared Task, Proceedings

Dokumenttyp

Konferensbidrag

Ämne

  • Computer Science

Conference name

The 15th Conference on Computational Natural Language Learning (CoNLL-2011): Shared Task

Conference date

2011-06-23 - 2011-06-24

Aktiv

Published

ISBN/ISSN/Övrigt

  • ISBN: 9781937284084