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.
Cite
@article{arxiv.1906.11565,
title = {EmotionX-KU: BERT-Max based Contextual Emotion Classifier},
author = {Kisu Yang and Dongyub Lee and Taesun Whang and Seolhwa Lee and Heuiseok Lim},
journal= {arXiv preprint arXiv:1906.11565},
year = {2019}
}
Comments
The 7th International Workshop on Natural Language Processing for Social Media (in conjunction with IJCAI 2019); figure modified