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


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 few-shot 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.

In the Meta Learning and Its Applications to Natural Language Processing workshop at ACL 2021
Gaël Guibon
Gaël Guibon
Post-doctoral Researcher

My research goes from emojis and emotion prediction and recommendation to French lexical evolution studies.