Learning Rich Event Representations and ...
Document type :
Communication dans un congrès avec actes
Title :
Learning Rich Event Representations and Interactions for Temporal Relation Classification
Author(s) :
Pandit, Onkar [Auteur]
Machine Learning in Information Networks [MAGNET]
Denis, Pascal [Auteur]
Machine Learning in Information Networks [MAGNET]
Ralaivola, Liva [Auteur]
Criteo [Paris]
éQuipe d'AppRentissage de MArseille [QARMA]
Machine Learning in Information Networks [MAGNET]
Denis, Pascal [Auteur]

Machine Learning in Information Networks [MAGNET]
Ralaivola, Liva [Auteur]
Criteo [Paris]
éQuipe d'AppRentissage de MArseille [QARMA]
Conference title :
ESANN 2019 - 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
City :
Bruges
Country :
Belgique
Start date of the conference :
2019-04-24
Book title :
ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Traitement du texte et du document
Informatique [cs]/Informatique et langage [cs.CL]
Informatique [cs]/Traitement du texte et du document
Informatique [cs]/Informatique et langage [cs.CL]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-02265061/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02265061/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02265061/document
- Open access
- Access the document
- document
- Open access
- Access the document
- ESANN_113.pdf
- Open access
- Access the document