Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation
This work addresses the need for more human-like dialogue systems by enhancing emotional awareness, but it is incremental as it builds on existing pre-trained models and multi-task learning techniques.
The paper tackled the problem of generating emotionally aware dialogue responses by proposing a multi-task learning model based on BART that simultaneously generates responses and recognizes emotions, with results showing improved emotional awareness in generated responses as confirmed by automatic and manual evaluations.
For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis et al., 2020), a pre-trained transformer encoder-decoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.