InferEM: Inferring the Speaker's Intention for Empathetic Dialogue Generation

TL;DR

InferEM is a novel model for empathetic dialogue generation that explicitly captures the speaker's intention from the last utterance and uses multi-task learning to improve empathetic responses.

Contribution

The paper introduces InferEM, which separately encodes the last utterance and fuses it with dialogue context, enhancing empathetic response generation by capturing speaker intention.

Findings

InferEM outperforms baseline models in empathetic response quality.

Explicit intention modeling improves dialogue response relevance.

Multi-task learning balances prediction and response generation effectively.

Abstract

Current approaches to empathetic response generation typically encode the entire dialogue history directly and put the output into a decoder to generate friendly feedback. These methods focus on modelling contextual information but neglect capturing the direct intention of the speaker. We argue that the last utterance in the dialogue empirically conveys the intention of the speaker. Consequently, we propose a novel model named InferEM for empathetic response generation. We separately encode the last utterance and fuse it with the entire dialogue through the multi-head attention based intention fusion module to capture the speaker's intention. Besides, we utilize previous utterances to predict the last utterance, which simulates human's psychology to guess what the interlocutor may speak in advance. To balance the optimizing rates of the utterance prediction and response generation, a multi-task learning strategy is designed for InferEM. Experimental results demonstrate the plausibility and validity of InferEM in improving empathetic expression.