EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments

TL;DR

EmpBot is an end-to-end empathetic chatbot based on T5 that integrates sentiment understanding and empathy objectives during training to generate more empathetic and relevant responses, outperforming current state-of-the-art models.

Contribution

We propose a novel T5-based training approach with auxiliary sentiment and empathy objectives for improved empathetic response generation.

Findings

EmpBot outperforms existing models on the EmpatheticDialogues dataset.

Auxiliary sentiment and empathy losses improve response empathy.

Human evaluations favor EmpBot's responses over baselines.

Abstract

In this paper, we introduce EmpBot: an end-to-end empathetic chatbot. Empathetic conversational agents should not only understand what is being discussed, but also acknowledge the implied feelings of the conversation partner and respond appropriately. To this end, we propose a method based on a transformer pretrained language model (T5). Specifically, during finetuning we propose to use three objectives: response language modeling, sentiment understanding, and empathy forcing. The first objective is crucial for generating relevant and coherent responses, while the next ones are significant for acknowledging the sentimental state of the conversational partner and for favoring empathetic responses. We evaluate our model on the EmpatheticDialogues dataset using both automated metrics and human evaluation. The inclusion of the sentiment understanding and empathy forcing auxiliary losses favor empathetic responses, as human evaluation results indicate, comparing with the current state-of-the-art.