An assential aspect of structured predic- tion is the evaluation of an output struc- ture against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely limited the expressivity of effec- tive loss functions. In this paper, we trade off exact computation for enabling the use of more complex loss functions for coreference resolution (CR). Most note- worthily, we show that such functions can be (i) automatically learned also from controversial but commonly accepted CR measures, e.g., MELA, and (ii) success- fully used in learning algorithms. The ac- curate model comparison on the standard CoNLL–2012 setting shows the benefit of more expressive loss for Arabic and En- glish data.



Titolo: Don’t understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
Autori: Iryna, Haponchyk; Alessandro, Moschitti
Autori Unitn: 
Haponchyk, Iryna
Moschitti, Alessandro
Titolo del volume contenente il saggio: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers
Luogo di edizione: Vancouver, Canada
Casa editrice: ACL 2017
Anno di pubblicazione: 2017
ISBN: 978-1-945626-75-3
Handle: http://hdl.handle.net/11572/195373
Citazione: Don’t understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures / Iryna, Haponchyk; Alessandro, Moschitti. - ELETTRONICO. - (2017), pp. 1018-1028.
Appare nelle tipologie:02.1 Saggio su volume miscellaneo o Capitolo di libro (Essay or Book Chapter)

File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
 
 
 
Powered by IRIS-about IRIS-Utilizzo dei cookie
Logo CINECA  Copyright © 2020