Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations
This work addresses the problem of improving emotion detection for applications like opinion mining in social networks, representing an incremental advance by combining existing techniques with knowledge integration.
The paper tackles emotion detection in textual conversations by proposing a Knowledge-Enriched Transformer (KET) that uses hierarchical self-attention and context-aware affective graph attention to incorporate context and commonsense knowledge, resulting in outperforming state-of-the-art models on most datasets in F1 score.
Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze emotions in conversations is challenging, partly because humans often rely on the context and commonsense knowledge to express emotions. In this paper, we address these challenges by proposing a Knowledge-Enriched Transformer (KET), where contextual utterances are interpreted using hierarchical self-attention and external commonsense knowledge is dynamically leveraged using a context-aware affective graph attention mechanism. Experiments on multiple textual conversation datasets demonstrate that both context and commonsense knowledge are consistently beneficial to the emotion detection performance. In addition, the experimental results show that our KET model outperforms the state-of-the-art models on most of the tested datasets in F1 score.