Use Generalized Representations, But Do Not Forget Surface Features

Nafise Sadat Moosavi, Michael Strube


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.
Anthology ID:
W17-1501
Volume:
Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017)
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Maciej Ogrodniczuk, Vincent Ng
Venue:
CORBON
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–7
Language:
URL:
https://aclanthology.org/W17-1501
DOI:
10.18653/v1/W17-1501
Bibkey:
Cite (ACL):
Nafise Sadat Moosavi and Michael Strube. 2017. Use Generalized Representations, But Do Not Forget Surface Features. In Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), pages 1–7, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Use Generalized Representations, But Do Not Forget Surface Features (Moosavi & Strube, CORBON 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-dup-bibkey/W17-1501.pdf
Data
WikiCoref