EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogue
This work addresses emotion detection in dialogue for applications like conversational AI, but it is incremental as it builds on existing BiLSTM and attention methods.
The paper tackled the problem of detecting sequential emotions in dialogue by proposing a self-attentive BiLSTM network, achieving unweighted accuracy scores of 59.6 on the Friends test set and 55.0 on the EmotionPush test set.
In this paper, we propose a self-attentive bidirectional long short-term memory (SA-BiLSTM) network to predict multiple emotions for the EmotionX challenge. The BiLSTM exhibits the power of modeling the word dependencies, and extracting the most relevant features for emotion classification. Building on top of BiLSTM, the self-attentive network can model the contextual dependencies between utterances which are helpful for classifying the ambiguous emotions. We achieve 59.6 and 55.0 unweighted accuracy scores in the \textit{Friends} and the \textit{EmotionPush} test sets, respectively.