An Iterative Associative Memory Model for Empathetic Response Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zhou, Ren, Zhaochun, Wang, Yufeng, Chen, Chao, Sun, Haizhou, Zhu, Xiaofei, Liao, Xiangwen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929369030590464
author Yang, Zhou
Ren, Zhaochun
Wang, Yufeng
Chen, Chao
Sun, Haizhou
Zhu, Xiaofei
Liao, Xiangwen
author_facet Yang, Zhou
Ren, Zhaochun
Wang, Yufeng
Chen, Chao
Sun, Haizhou
Zhu, Xiaofei
Liao, Xiangwen
contents Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates iteratively capturing and understanding associated words across dialogue utterances. However, existing approaches regard dialogue utterances as either a long sequence or independent utterances for comprehension, which are prone to overlook the associated words between them. To address this issue, we propose an Iterative Associative Memory Model (IAMM) for empathetic response generation. Specifically, we employ a novel second-order interaction attention mechanism to iteratively capture vital associated words between dialogue utterances and situations, dialogue history, and a memory module (for storing associated words), thereby accurately and nuancedly comprehending the utterances. We conduct experiments on the Empathetic-Dialogue dataset. Both automatic and human evaluations validate the efficacy of the model. Variant experiments on LLMs also demonstrate that attending to associated words improves empathetic comprehension and expression.
format Preprint
id arxiv_https___arxiv_org_abs_2402_17959
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Iterative Associative Memory Model for Empathetic Response Generation
Yang, Zhou
Ren, Zhaochun
Wang, Yufeng
Chen, Chao
Sun, Haizhou
Zhu, Xiaofei
Liao, Xiangwen
Computation and Language
Human-Computer Interaction
Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates iteratively capturing and understanding associated words across dialogue utterances. However, existing approaches regard dialogue utterances as either a long sequence or independent utterances for comprehension, which are prone to overlook the associated words between them. To address this issue, we propose an Iterative Associative Memory Model (IAMM) for empathetic response generation. Specifically, we employ a novel second-order interaction attention mechanism to iteratively capture vital associated words between dialogue utterances and situations, dialogue history, and a memory module (for storing associated words), thereby accurately and nuancedly comprehending the utterances. We conduct experiments on the Empathetic-Dialogue dataset. Both automatic and human evaluations validate the efficacy of the model. Variant experiments on LLMs also demonstrate that attending to associated words improves empathetic comprehension and expression.
title An Iterative Associative Memory Model for Empathetic Response Generation
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2402.17959