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.

protoseq

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

quasar-awesome

🎉 A list of awesome things related to Quasar

relationextraction

semeval2018-task2-multilingualemojiprediction

Source code for our system sent to the task 2 of SemEval2018

sideshow

Sideshow is a powerful javascript library which aims to reduce your user's learning curve by providing a way to create step-by-step interactive tours. Explain the features of your application, control your end-user's interaction with your UI, emphasize what you're explaining in each step by masking it. Just think! The sky is the limit!

gguibon Goto Github PK

Gaël Guibon's Projects

Recommend Projects

Recommend Topics

Recommend Org