Discourse parsing for multi-party chat dialogues - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Discourse parsing for multi-party chat dialogues

Abstract

In this paper we present the first ever, to the best of our knowledge, discourse parser for multi-party chat dialogues. Discourse in multi-party dialogues dramatically differs from monologues since threaded conversations are commonplace rendering prediction of the discourse structure compelling. Moreover, the fact that our data come from chats renders the use of syntactic and lexical information useless since people take great liberties in expressing themselves lexically and syntactically. We use the dependency parsing paradigm as has been done in the past (Muller et al., 2012; Li et al., 2014). We learn local probability distributions and then use MST for decoding. We achieve 0.680 F 1 on unlabelled structures and 0.516 F 1 on fully labeled structures which is better than many state of the art systems for monologues, despite the inherent difficulties that multi-party chat dialogues have.
Fichier principal
Vignette du fichier
afantenos_16912.pdf (203.94 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01535954 , version 1 (09-06-2017)

Identifiers

  • HAL Id : hal-01535954 , version 1
  • OATAO : 16912

Cite

Stergos Afantenos, Eric Kow, Nicholas Asher, Jérémy Perret. Discourse parsing for multi-party chat dialogues. Conference on Empirical Methods on Natural Language Processing (EMNLP 2015), Sep 2015, Lisbon, Portugal. pp. 928-937. ⟨hal-01535954⟩
283 View
111 Download

Share

Gmail Facebook Twitter LinkedIn More