EmotionX-IDEA: Emotion BERT -- an Affectional Model for Conversation
This addresses emotion prediction in conversations for applications like chatbots, but it is incremental as it adapts an existing model to a specific task.
The paper tackled emotion recognition in continuous dialogue by adapting BERT to predict emotions based on causal utterance pairs, achieving micro F1 scores of 0.815 on Friends and 0.885 on EmotionPush datasets.
In this paper, we investigate the emotion recognition ability of the pre-training language model, namely BERT. By the nature of the framework of BERT, a two-sentence structure, we adapt BERT to continues dialogue emotion prediction tasks, which rely heavily on the sentence-level context-aware understanding. The experiments show that by mapping the continues dialogue into a causal utterance pair, which is constructed by the utterance and the reply utterance, models can better capture the emotions of the reply utterance. The present method has achieved 0.815 and 0.885 micro F1 score in the testing dataset of Friends and EmotionPush, respectively.