Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations

IJCNLP 2019  ·  Peixiang Zhong, Di Wang, Chunyan Miao ·

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.

PDF Abstract IJCNLP 2019 PDF IJCNLP 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Emotion Recognition in Conversation DailyDialog KET Micro-F1 53.37 # 18
Emotion Recognition in Conversation EC KET Micro-F1 0.7413 # 8
Emotion Recognition in Conversation EmoryNLP KET Weighted-F1 34.39 # 24
Emotion Recognition in Conversation IEMOCAP KET Weighted-F1 61.33 # 41
Micro-F1 61.11 # 2
Emotion Recognition in Conversation MELD KET Weighted-F1 58.18 # 48

Methods