# CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification

## TL;DR

This paper presents a hierarchical neural network approach for dialogue emotion classification, leveraging previous emotional context to improve accuracy, and achieves a state-of-the-art F1-score of 76.77%.

## Contribution

It introduces a hierarchical model that considers emotional dependencies across dialogue turns, outperforming existing classifiers in dialogue emotion detection.

## Key findings

- Hierarchical models significantly outperform non-hierarchical baselines.
- Best model achieves 76.77% F1-score on test data.
- Feature-based and neural models are benchmarked with consistent improvements.

## 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.