Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition

Imagine telling your chatbot that your dog just died. Instead In this work, we introduce Knowledge-Embedded Attention of correctly understanding that you are experiencing grief (and (KEA), a knowledge-augmented attention mechanism that offering condolences), it classifies you as feeling sad and offers enriches the contextual representation provided by pre-trained to play you a happy song to cheer you up. People experience language models using emotional information obtained from a wide range of emotions, and it is important for AI agents external knowledge sources. This is achieved by incorporating to correctly recognize subtle differences between emotions the encoded emotional knowledge with the contextual representations like sadness and grief, in order to improve their interactions to form a modified key matrix. This key matrix with people and to avoid making a faux pas like the chatbot is then used to attend to the contextual representations to above [1]. Traditionally, the vast majority of work in emotion construct a more emotionally-aware representation of the input recognition from text focuses on recognizing just six "basic" text that can be used to recognise emotions. We introduce two emotions [2], [3], usually happiness, surprise, sadness, anger, variants of KEA, (i) a word-level KEA and (ii) a sentencelevel disgust, and fear. This set clearly fails to capture the broad KEA, which incorporate knowledge at different text spectrum of emotions that people experience and express in granularities.