Integer Linear Programming for Discourse Parsing - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Integer Linear Programming for Discourse Parsing


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.
Fichier principal
Vignette du fichier
perret_22644.pdf (237.96 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02124414 , version 1 (09-05-2019)


  • HAL Id : hal-02124414 , version 1
  • OATAO : 22644


Jérémy Perret, Stergos Afantenos, Nicholas Asher, Mathieu Morey. Integer Linear Programming for Discourse Parsing. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016), Jun 2016, San Diego, California, United States. pp.99-109. ⟨hal-02124414⟩
73 View
99 Download


Gmail Facebook X LinkedIn More