Skip to Main content Skip to Navigation
Conference papers

Improving pairwise coreference models through feature space hierarchy learning

Emmanuel Lassalle 1 Pascal Denis 2
1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
Inria Paris-Rocquencourt, UPD7 - Université Paris Diderot - Paris 7
2 MAGNET - Machine Learning in Information Networks
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
Abstract : This paper proposes a new method for significantly improving the performance of pairwise coreference models. Given a set of indicators, our method learns how to best separate types of mention pairs into equivalence classes for which we construct distinct classification models. In effect, our approach finds an optimal feature space (derived from a base feature set and indicator set) for discriminating coreferential mention pairs. Although our approach explores a very large space of possible feature spaces, it remains tractable by exploiting the structure of the hierarchies built from the indicators. Our experiments on the CoNLL-2012 Shared Task English datasets (gold mentions) indicate that our method is robust relative to different clustering strategies and evaluation metrics, showing large and consistent improvements over a single pairwise model using the same base features. Our best system obtains a competitive 67:2 of average F1 over MUC, B3 , and CEAF which, despite its simplicity, places it above the mean score of other systems on these datasets.
Document type :
Conference papers
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Pascal Denis Connect in order to contact the contributor
Submitted on : Tuesday, June 25, 2013 - 8:41:10 AM
Last modification on : Friday, January 21, 2022 - 3:21:44 AM
Long-term archiving on: : Thursday, September 26, 2013 - 4:18:38 AM


Files produced by the author(s)


  • HAL Id : hal-00838192, version 1


Emmanuel Lassalle, Pascal Denis. Improving pairwise coreference models through feature space hierarchy learning. ACL 2013 - Annual meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Aug 2013, Sofia, Bulgaria. ⟨hal-00838192⟩



Les métriques sont temporairement indisponibles