Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation

TL;DR

This paper introduces a multi-task learning model based on BART that simultaneously generates dialogue responses and recognizes emotions, enhancing emotional awareness in AI interactions.

Contribution

It presents a novel multi-task learning approach combining response generation and emotion classification using a pre-trained transformer model.

Findings

Responses are more emotionally aware in automatic evaluations.

Crowdsourced evaluations confirm improved emotional relevance.

The model effectively balances generation and classification tasks.

Abstract

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.