Multi-task Learning for Semantic Relations Discovery

Georgios Balikas 1 Gaël Dias 2 Massih-Reza Amini Houssam Akhmouch 3, 2
2 Equipe Hultech - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Identifying the semantic relations that hold between words is of crucial importance for reasoning purposes. Within this context, different methodolo-gies have been proposed that either exclusively focus on a single lexical relation (two-class problem) or learn specific classifiers capable of identifying multiple semantic relations (multi-class problem). In this paper, we propose another way to look at the problem that relies on the multi-task learning paradigm. Preliminary results based on simple learning strategies and state-of-the-art distributional feature representations show that concurrent learning can lead to improvements.
Type de document :
Communication dans un congrès
21st International Conference on Knowledge Engineering and Knowledge Management (EKAW 2018), 2018, Nancy, France
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01921715
Contributeur : Gaël Dias <>
Soumis le : mercredi 14 novembre 2018 - 09:03:14
Dernière modification le : jeudi 7 février 2019 - 17:38:30
Document(s) archivé(s) le : vendredi 15 février 2019 - 12:49:39

Fichier

EKAW_2018___Multi_task_Learnin...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01921715, version 1

Citation

Georgios Balikas, Gaël Dias, Massih-Reza Amini, Houssam Akhmouch. Multi-task Learning for Semantic Relations Discovery. 21st International Conference on Knowledge Engineering and Knowledge Management (EKAW 2018), 2018, Nancy, France. 〈hal-01921715〉

Partager

Métriques

Consultations de la notice

38

Téléchargements de fichiers

20