Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation (2105.08316v3)

Published 18 May 2021 in cs.CL

Abstract: The capacity of empathy is crucial to the success of open-domain dialog systems. Due to its nature of multi-dimensionality, there are various factors that relate to empathy expression, such as communication mechanism, dialog act and emotion. However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling. In this paper, we propose a multi-factor hierarchical framework, CoMAE, for empathetic response generation, which models the above three key factors of empathy expression in a hierarchical way. We show experimentally that our CoMAE-based model can generate more empathetic responses than previous methods. We also highlight the importance of hierarchical modeling of different factors through both the empirical analysis on a real-life corpus and the extensive experiments. Our codes and used data are available at https://github.com/chujiezheng/CoMAE.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Chujie Zheng (35 papers)
  2. Yong Liu (721 papers)
  3. Wei Chen (1288 papers)
  4. Yongcai Leng (1 paper)
  5. Minlie Huang (225 papers)
Citations (67)