OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Integer Linear Programming for Discourse Parsing

Perret, Jérémy and Afantenos, Stergos and Asher, Nicholas and Morey, Mathieu Integer Linear Programming for Discourse Parsing. (2016) In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016), 12 June 2016 - 17 June 2016 (San Diego, California, United States).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
243kB

Official URL: https://doi.org/10.18653/v1/N16-1013

Abstract

In this paper we present the first, to the best of our knowledge, discourse parser that is able to predict non-tree DAG structures. We use Integer Linear Programming (ILP) to encode both the objective function and the constraints as global decoding over local scores. Our underlying data come from multi-party chat dialogues, which require the prediction of DAGs. We use the dependency parsing paradigm, as has been done in the past (Muller et al., 2012; Li et al., 2014; Afantenos et al., 2015), but we use the underlying formal framework of SDRT and exploit SDRT's notions of left and right distributive relations. We achieve an F-measure of 0.531 for fully labeled structures which beats the previous state of the art.

Item Type:Conference or Workshop Item (Paper)
Additional Information:https://aclweb.org/anthology/N16-1000 ISBN 978-1-941643-91-4
HAL Id:hal-02124414
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut National Polytechnique de Toulouse - INPT (FRANCE)
French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UPS (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Laboratory name:
Statistics:download
Deposited By: IRIT IRIT
Deposited On:08 Apr 2019 12:20

Repository Staff Only: item control page