# Exploiting Emotion-Semantic Correlations for Empathetic Response Generation

arXiv: https://arxiv.org/abs/2402.17437 · HTML: https://mlsanity.com/paper/2402.17437/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [MIME: MIMicking Emotions for Empathetic Response Generation](https://mlsanity.com/paper/2010.01454/) (2020)
- [CEM: Commonsense-aware Empathetic Response Generation](https://mlsanity.com/paper/2109.05739/) (2021)
- [Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://mlsanity.com/paper/1603.04351/) (2016)
- [Towards Persona-Based Empathetic Conversational Models](https://mlsanity.com/paper/2004.12316/) (2020)
- [Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes](https://mlsanity.com/paper/2109.08828/) (2021)
- [CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation](https://mlsanity.com/paper/2105.08316/) (2021)
- [CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts](https://mlsanity.com/paper/2012.08377/) (2020)
- [What Do Recurrent Neural Network Grammars Learn About Syntax?](https://mlsanity.com/paper/1611.05774/) (2016)
- [Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances](https://mlsanity.com/paper/2205.03112/) (2022)
- [CASS: Towards Building a Social-Support Chatbot for Online Health Community](https://mlsanity.com/paper/2101.01583/) (2021)

## Built on by (most cited first, 5 of 5)

- [Towards Empathetic Conversational Recommender Systems](https://mlsanity.com/paper/2409.10527/) (2024)
- [An Iterative Associative Memory Model for Empathetic Response Generation](https://mlsanity.com/paper/2402.17959/) (2024)
- [Emotion Recognition and Generation: A Comprehensive Review of Face, Speech, and Text Modalities](https://mlsanity.com/paper/2502.06803/) (2025)
- [E-ICL: Enhancing Fine-Grained Emotion Recognition through the Lens of Prototype Theory](https://mlsanity.com/paper/2406.02642/) (2024)
- [Dynamic Commonsense Coordination for Empathetic Response Generation](https://mlsanity.com/paper/2607.22136/) (2026)

## Abstract (arXiv)

Empathetic response generation aims to generate empathetic responses by understanding the speaker's emotional feelings from the language of dialogue. Recent methods capture emotional words in the language of communicators and construct them as static vectors to perceive nuanced emotions. However, linguistic research has shown that emotional words in language are dynamic and have correlations with other grammar semantic roles, i.e., words with semantic meanings, in grammar. Previous methods overlook these two characteristics, which easily lead to misunderstandings of emotions and neglect of key semantics. To address this issue, we propose a dynamical Emotion-Semantic Correlation Model (ESCM) for empathetic dialogue generation tasks. ESCM constructs dynamic emotion-semantic vectors through the interaction of context and emotions. We introduce dependency trees to reflect the correlations between emotions and semantics. Based on dynamic emotion-semantic vectors and dependency trees, we propose a dynamic correlation graph convolutional network to guide the model in learning context meanings in dialogue and generating empathetic responses. Experimental results on the EMPATHETIC-DIALOGUES dataset show that ESCM understands semantics and emotions more accurately and expresses fluent and informative empathetic responses. Our analysis results also indicate that the correlations between emotions and semantics are frequently used in dialogues, which is of great significance for empathetic perception and expression.