Skip to Main content Skip to Navigation
Conference papers

Learning Rich Event Representations and Interactions for Temporal Relation Classification

Onkar Pandit 1 Pascal Denis 1 Liva Ralaivola 2, 3
1 MAGNET - Machine Learning in Information Networks
CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189, Inria Lille - Nord Europe
2 QARMA - éQuipe d'AppRentissage de MArseille
LIS - Laboratoire d'Informatique et Systèmes
Abstract : 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.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download
Contributor : Team Magnet <>
Submitted on : Thursday, August 8, 2019 - 12:04:52 PM
Last modification on : Monday, January 13, 2020 - 12:14:00 PM
Document(s) archivé(s) le : Thursday, January 9, 2020 - 2:51:12 AM


Files produced by the author(s)


  • HAL Id : hal-02265061, version 1


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⟩



Record views


Files downloads