Implicit Discourse Relation Classification with Syntax-Aware Contextualized Word Representations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Implicit Discourse Relation Classification with Syntax-Aware Contextualized Word Representations

Julien Perez
  • Fonction : Auteur
  • PersonId : 1111018
James Henderson
  • Fonction : Auteur
  • PersonId : 1111019
Éric Gaussier

Résumé

Automatically identifying implicit discourse relations requires an in-depth semantic understanding of the text fragments involved in such relations. While early work investigated the usefulness of different classes of input features, current state-of-the-art models mostly rely on standard pretrained word embeddings to model the arguments of a discourse relation. In this paper, we introduce a method to compute contextualized representations of words, leveraging information from the sentence dependency parse, to improve argument representation. The resulting token embeddings encode the structure of the sentence from a dependency point of view in their representations. Experimental results show that the proposed representations achieve state-of-the-art results when input to standard neural network architectures, surpassing complex models that use additional data and consider the interaction between arguments.
Fichier principal
Vignette du fichier
18303-78922-1-PB.pdf (532.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03352337 , version 1 (23-09-2021)

Identifiants

  • HAL Id : hal-03352337 , version 1

Citer

Diana Nicoleta Popa, Julien Perez, James Henderson, Éric Gaussier. Implicit Discourse Relation Classification with Syntax-Aware Contextualized Word Representations. 32nd FLAIRS Conference 2019: Sarasota, Florida, USA, 2019, Florida, USA, United States. ⟨hal-03352337⟩
102 Consultations
30 Téléchargements

Partager

Gmail Facebook X LinkedIn More