@InProceedings{winata-EtAl:2019:S19-2,
  author    = {Winata, Genta Indra  and  Madotto, Andrea  and  Lin, Zhaojiang  and  Shin, Jamin  and  Xu, Yan  and  Xu, Peng  and  Fung, Pascale},
  title     = {CAiRE\_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification},
  booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation},
  month     = {June},
  year      = {2019},
  address   = {Minneapolis, Minnesota, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {142--147},
  abstract  = {Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed. One could consider the emotion of each dialogue turn to be independent, but in this paper, we introduce a hierarchical approach to classify emotion, hypothesizing that the current emotional state depends on previous latent emotions. We benchmark several feature-based classifiers using pre-trained word and emotion embeddings, state-of-the-art end-to-end neural network models, and Gaussian processes for automatic hyper-parameter search. In our experiments, hierarchical architectures consistently give significant improvements, and our best model achieves a 76.77\% F1-score on the test set.},
  url       = {http://www.aclweb.org/anthology/S19-2021}
}