Improving pairwise coreference models through feature space hierarchy learning

Lassalle, Emmanuel; Denis, Pascal

Document type :

Communication dans un congrès avec actes

Title :

Improving pairwise coreference models through feature space hierarchy learning

Author(s) :

Lassalle, Emmanuel [Auteur]
Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing [ALPAGE]
Denis, Pascal [Auteur]

Machine Learning in Information Networks [MAGNET]

Conference title :

ACL 2013 - Annual meeting of the Association for Computational Linguistics

Conference organizers(s) :

Association for Computational Linguistics

City :

Sofia

Country :

Bulgarie

Start date of the conference :

2013-08-04

Publication date :

2013

HAL domain(s) :

Informatique [cs]/Informatique et langage [cs.CL]

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

https://hal.inria.fr/hal-00838192/document
Open access
Access the document

https://hal.inria.fr/hal-00838192/document
Open access
Access the document

https://hal.inria.fr/hal-00838192/document
Open access
Access the document

Improving pairwise coreference models ... BibTeX CSV Excel RIS

Files

Improving pairwise coreference models ...

BibTeX

CSV

Excel

RIS