# Modeling Content-Emotion Duality via Disentanglement for Empathetic Conversation

arXiv: https://arxiv.org/abs/2209.12495 · HTML: https://mlsanity.com/paper/2209.12495/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [MoEL: Mixture of Empathetic Listeners](https://mlsanity.com/paper/1908.07687/) (2019)
- [MojiTalk: Generating Emotional Responses at Scale](https://mlsanity.com/paper/1711.04090/) (2017)
- [Affect-Driven Dialog Generation](https://mlsanity.com/paper/1904.02793/) (2019)
- [CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation](https://mlsanity.com/paper/2005.00329/) (2020)
- [A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation](https://mlsanity.com/paper/1806.07000/) (2018)
- [Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality](https://mlsanity.com/paper/2110.04614/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation](https://mlsanity.com/paper/2406.09881/) (2024)

## Abstract (arXiv)

The task of empathetic response generation aims to understand what feelings a speaker expresses on his/her experiences and then reply to the speaker appropriately. To solve the task, it is essential to model the content-emotion duality of a dialogue, which is composed of the content view (i.e., what personal experiences are described) and the emotion view (i.e., the feelings of the speaker on these experiences). To this end, we design a framework to model the Content-Emotion Duality (CEDual) via disentanglement for empathetic response generation. With disentanglement, we encode the dialogue history from both the content and emotion views, and then generate the empathetic response based on the disentangled representations, thereby both the content and emotion information of the dialogue history can be embedded in the generated response. The experiments on the benchmark dataset EMPATHETICDIALOGUES show that the CEDual model achieves state-of-the-art performance on both automatic and human metrics, and it also generates more empathetic responses than previous methods.