Meta-learning for Classifying Previously Unseen Data Source into Previously Unseen Emotional Categories - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Meta-learning for Classifying Previously Unseen Data Source into Previously Unseen Emotional Categories

Résumé

In this paper, we place ourselves in a classification scenario in which the target classes and data type are not accessible during training. We use a meta-learning approach to determine whether or not meta-trained information from common social network data with fine-grained emotion labels can achieve competitive performance on messages labeled with different emotion categories. We leverage fewshot learning to match with the classification scenario and consider metric learning based meta-learning by setting up Prototypical Networks with a Transformer encoder, trained in an episodic fashion. This approach proves to be effective for capturing meta-information from a source emotional tag set to predict previously unseen emotional tags. Even though shifting the data type triggers an expected performance drop, our meta-learning approach achieves decent results when compared to the fully supervised one.
Fichier principal
Vignette du fichier
metalearning-aclmetanlp2021.pdf (665.93 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03563675 , version 1 (09-02-2022)

Identifiants

  • HAL Id : hal-03563675 , version 1

Citer

Gaël Guibon, Matthieu Labeau, Hélène Flamein, Luce Lefeuvre, Chloé Clavel. Meta-learning for Classifying Previously Unseen Data Source into Previously Unseen Emotional Categories. 1st Workshop on Meta Learning and Its Applications to Natural Language Processing, ACL 2021, Aug 2021, Bangkok, Thailand. ⟨hal-03563675⟩
54 Consultations
59 Téléchargements

Partager

Gmail Facebook X LinkedIn More