EmotionX-KU: BERT-Max based Contextual Emotion Classifier

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.

arXiv commentThe 7th International Workshop on Natural Language Processing for Social Media (in conjunction with IJCAI 2019); figure modified

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• SGDR: Stochastic Gradient Descent with Warm Restarts
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks
• EmotionLines: An Emotion Corpus of Multi-Party Conversations
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction

Cited by in corpus (2)

• SocialNLP EmotionX 2019 Challenge Overview: Predicting Emotions in Spoken Dialogues and Chats
• Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?