Moosavi, N.S. orcid.org/0000-0002-8332-307X and Strube, M. (2017) Use generalized representations, but do not forget surface features. In: Ogrodniczuk, M. and Ng, V., (eds.) Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017). 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), 04 Apr 2017, Valencia, Spain. Association for Computational Linguistics , pp. 1-7. ISBN 9781945626463
Abstract
Only a year ago, all state-of-the-art coreference resolvers were using an extensive amount of surface features. Recently, there was a paradigm shift towards using word embeddings and deep neural networks, where the use of surface features is very limited. In this paper, we show that a simple SVM model with surface features outperforms more complex neural models for detecting anaphoric mentions. Our analysis suggests that using generalized representations and surface features have different strength that should be both taken into account for improving coreference resolution.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2017 Association for Computational Linguistics. Available under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/). |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 07 Sep 2022 11:31 |
Last Modified: | 07 Sep 2022 14:28 |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Refereed: | Yes |
Identification Number: | 10.18653/v1/w17-1501 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:190607 |