计算机应用研究2025，Vol.42Issue(6)：1706-1712,7.DOI:10.19734/j.issn.1001-3695.2024.11.0468
基于ABSA与动态少样本提示的主观知识对话回复生成模型
Subjective knowledge dialogue response generation model based on ABSA and dynamic few-shot prompting
摘要
Abstract
In the latest task-oriented dialogue system challenges,effectively utilizing subjective knowledge(e.g.,personal opinions)is crucial for addressing users' specific needs.However,due to the inherently subjective nature of such knowledge,how to effectively integrate and leverage this information has become a key focus of research.This paper proposed a method called DynSense,aimed at addressing the challenge of generating comprehensive and generalized responses from multiple rele-vant subjective user opinions.DynSense firstly employed aspect-based sentiment analysis(ABSA)to parse the aspects and sentiment polarities within subjective knowledge snippets,aligning them with the user's query.Then,it utilized an advanced dialogue model that combined the dialogue context with ABSA-enhanced information to generate responses.A specially de-signed DynMatch algorithm guided the model to generate more relevant responses by dynamically selecting high-quality know-ledge fragments most similar to the current query as few-shot prompts.The experimental results demonstrate that DynSense ex-hibits exceptional ability in capturing latent semantic features and emotional tendencies,generating precise,comprehensive,and highly aligned responses based on past user reviews.Compared to existing models,DynSense shows significant improve-ments across various evaluation metrics on the SK-TOD benchmark.关键词
任务导向型对话系统/主观知识/基于方面项的情感分析/动态少样本提示Key words
task-oriented dialogue systems/subjective knowledge/aspect-based sentiment analysis(ABSA)/dynamic few-shot prompts分类
信息技术与安全科学引用本文复制引用
饶东宁,庄杰涛..基于ABSA与动态少样本提示的主观知识对话回复生成模型[J].计算机应用研究,2025,42(6):1706-1712,7.基金项目
广东省自然科学基金面上项目(2021A1515012556) （2021A1515012556）
