计算机应用研究2024，Vol.41Issue(10)：2993-2999,7.DOI:10.19734/j.issn.1001-3695.2024.03.0048
融合背景知识和常识感知的对话生成
Integration of background knowledge and common sense perception for dialogue generation
摘要
Abstract
One of the key issues in background-based conversation is knowledge extraction.However,due to the insufficient information in some conversations,especially when there is less information in certain dialogues,choosing the appropriate knowledge becomes particularly challenging.Furthermore,the current generation methods lack the capability to dynamically se-lect background knowledge.To address these issues,this paper proposed the KIF model,which incorporated a knowledge en-hancement library and knowledge vectors and introduced a knowledge tracking module and a knowledge sentiment feedback module to solve the aforementioned problems.The model obtained weight vectors of external knowledge and background know-ledge through a dual matching matrix method and performs knowledge selection.For each decoding step,the model generated conversation based on historical dialogues and external knowledge.Finally,experiments on the Holl-E and WoW datasets show that the KIF model significantly outperforms previous models.关键词
背景知识/对话系统/自然语言处理Key words
background based/dialogue systems/natural language processing分类
信息技术与安全科学引用本文复制引用
汪红松,叶浩贤,李嘉展..融合背景知识和常识感知的对话生成[J].计算机应用研究,2024,41(10):2993-2999,7.基金项目
国家自然科学基金资助项目(62076103) （62076103）
广东省基础与应用基础研究基金资助项目(2021A15150117) （2021A15150117）
