A Unified Framework for Emotion Identification and Generation in Dialogues

TL;DR

This paper introduces a multi-task BERT-based framework that simultaneously identifies emotions in dialogues and generates emotionally appropriate responses, enhancing social chatbot interactions.

Contribution

It presents a novel joint emotion recognition and response generation model using a mixed objective function for improved empathetic dialogue systems.

Findings

Outperforms current state-of-the-art models in emotion-aware dialogue tasks.

Effectively combines emotion classification and response generation in a unified framework.

Demonstrates improved user engagement through emotionally intelligent responses.

Abstract

Social chatbots have gained immense popularity, and their appeal lies not just in their capacity to respond to the diverse requests from users, but also in the ability to develop an emotional connection with users. To further develop and promote social chatbots, we need to concentrate on increasing user interaction and take into account both the intellectual and emotional quotient in the conversational agents. In this paper, we propose a multi-task framework that jointly identifies the emotion of a given dialogue and generates response in accordance to the identified emotion. We employ a BERT based network for creating an empathetic system and use a mixed objective function that trains the end-to-end network with both the classification and generation loss. Experimental results show that our proposed framework outperforms current state-of-the-art models