Learning Rich Event Representations and Interactions for Temporal Relation Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Learning Rich Event Representations and Interactions for Temporal Relation Classification

Onkar Pandit
  • Fonction : Auteur
  • PersonId : 1052276
Pascal Denis

Résumé

Most existing systems for identifying temporal relations between events heavily rely on hand-crafted features derived from event words and explicit temporal markers. Besides, less attention has been given to automatically learning con-textualized event representations or to finding complex interactions between events. This paper fills this gap in showing that a combination of rich event representations and interaction learning is essential to more accurate temporal relation classification. Specifically, we propose a method in which i) Recurrent Neural Networks (RNN) extract contextual information ii) character embeddings capture morpho-semantic features (e.g. tense, mood, aspect), and iii) a deep Convolutional Neu-ral Network (CNN) finds out intricate interactions between events. We show that the proposed approach outperforms most existing systems on the commonly used dataset while using fully automatic feature extraction and simple local inference.
Fichier principal
Vignette du fichier
ESANN_113.pdf (165.68 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02265061 , version 1 (08-08-2019)

Identifiants

  • HAL Id : hal-02265061 , version 1

Citer

Onkar Pandit, Pascal Denis, Liva Ralaivola. Learning Rich Event Representations and Interactions for Temporal Relation Classification. ESANN 2019 - 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2019, Bruges, Belgium. ⟨hal-02265061⟩
209 Consultations
118 Téléchargements

Partager

Gmail Facebook X LinkedIn More