EmotionX-KU: BERT-Max based Contextual Emotion Classifier

TL;DR

This paper introduces a BERT-Max based contextual emotion classifier that effectively predicts emotions in dialogue by leveraging transfer learning, dynamic pooling, and domain adaptation techniques, outperforming previous models on benchmark datasets.

Contribution

The paper presents a novel emotion classification model combining BERT with dynamic max pooling and domain adaptation, achieving state-of-the-art results on EmotionX datasets.

Findings

Outperforms previous state-of-the-art models on Friends and EmotionPush datasets.

Demonstrates effective handling of contextual information and class imbalance.

Shows competitive performance in the EmotionX 2019 challenge.

Abstract

We propose a contextual emotion classifier based on a transferable language model and dynamic max pooling, which predicts the emotion of each utterance in a dialogue. A representative emotion analysis task, EmotionX, requires to consider contextual information from colloquial dialogues and to deal with a class imbalance problem. To alleviate these problems, our model leverages the self-attention based transferable language model and the weighted cross entropy loss. Furthermore, we apply post-training and fine-tuning mechanisms to enhance the domain adaptability of our model and utilize several machine learning techniques to improve its performance. We conduct experiments on two emotion-labeled datasets named Friends and EmotionPush. As a result, our model outperforms the previous state-of-the-art model and also shows competitive performance in the EmotionX 2019 challenge. The code will be available in the Github page.