Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Yeonju, Park, Se Jin, Ro, Yong Man
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915076871553024
author Kim, Yeonju
Park, Se Jin
Ro, Yong Man
author_facet Kim, Yeonju
Park, Se Jin
Ro, Yong Man
contents Chatbot research is advancing with the growing importance of chatbots in fields that require human interactions, such as customer support and mental health care. Despite these advancements, chatbots still face significant challenges in understanding subtle nuances and managing long conversation histories. To address these issues, our study introduces a dual approach: firstly, we employ Emotional Preference Optimization (EPO) to train chatbots not only with correct responses but also with counter-emotional responses-those that are contextually similar but emotionally divergent. This training enables the model to discern fine nuance distinctions between correct and counter-emotional responses, thereby enhancing the quality of its responses. Secondly, we introduce MambaCompressor to effectively compress and manage extensive conversation histories, significantly reducing time and memory complexities while improving the chatbot's contextual understanding. Our comprehensive experiments across multiple datasets demonstrate that our model significantly outperforms existing models in generating empathetic responses and efficiently managing lengthy dialogues.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17572
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor
Kim, Yeonju
Park, Se Jin
Ro, Yong Man
Computer Vision and Pattern Recognition
Artificial Intelligence
Chatbot research is advancing with the growing importance of chatbots in fields that require human interactions, such as customer support and mental health care. Despite these advancements, chatbots still face significant challenges in understanding subtle nuances and managing long conversation histories. To address these issues, our study introduces a dual approach: firstly, we employ Emotional Preference Optimization (EPO) to train chatbots not only with correct responses but also with counter-emotional responses-those that are contextually similar but emotionally divergent. This training enables the model to discern fine nuance distinctions between correct and counter-emotional responses, thereby enhancing the quality of its responses. Secondly, we introduce MambaCompressor to effectively compress and manage extensive conversation histories, significantly reducing time and memory complexities while improving the chatbot's contextual understanding. Our comprehensive experiments across multiple datasets demonstrate that our model significantly outperforms existing models in generating empathetic responses and efficiently managing lengthy dialogues.
title Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.17572