Skip to Main content Skip to Navigation
Conference papers

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

Abstract : 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.
Complete list of metadata

https://hal.telecom-paris.fr/hal-03563675
Contributor : Gaël Guibon Connect in order to contact the contributor
Submitted on : Wednesday, February 9, 2022 - 8:17:36 PM
Last modification on : Monday, April 25, 2022 - 9:36:01 AM
Long-term archiving on: : Tuesday, May 10, 2022 - 7:23:32 PM

File

metalearning-aclmetanlp2021.pd...
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-03563675, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

16

Files downloads

5