Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition
This work addresses the need for more empathetic AI interactions by enhancing emotion recognition systems to capture a broader spectrum of emotions, though it is incremental as it builds on existing pre-trained models.
The paper tackled the problem of fine-grained emotion recognition by introducing external knowledge from emotion lexicons into pre-trained language models like ELECTRA and BERT, resulting in improved performance on several datasets and better differentiation of closely-confusable emotions such as afraid and terrified.
Modern emotion recognition systems are trained to recognize only a small set of emotions, and hence fail to capture the broad spectrum of emotions people experience and express in daily life. In order to engage in more empathetic interactions, future AI has to perform \textit{fine-grained} emotion recognition, distinguishing between many more varied emotions. Here, we focus on improving fine-grained emotion recognition by introducing external knowledge into a pre-trained self-attention model. We propose Knowledge-Embedded Attention (KEA) to use knowledge from emotion lexicons to augment the contextual representations from pre-trained ELECTRA and BERT models. Our results and error analyses outperform previous models on several datasets, and is better able to differentiate closely-confusable emotions, such as afraid and terrified.