基于知识图谱中路径推理的多轮对话模型  

Multi Round Conversational Model Based on Path Reasoning in Knowledge Graph

作　　者：化青远 彭涛[1,2] 崔海 毕海嘉 HUA Qingyuan;PENG Tao;CUI Hai;BI Haijia(College of Computer Science and Technology,Jilin University,Changchun 130012,China;Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China)

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]吉林大学符号计算与知识工程教育部重点实验室,长春130012

出　　处：《吉林大学学报(理学版)》2025年第1期76-82,共7页Journal of Jilin University:Science Edition

基　　金：吉林省科技厅重点科技研发项目(批准号:20210201131GX).

摘　　要：基于图编码器的路径推理方法,将知识图谱多轮对话的实体间关系作为节点图,编码器根据每轮对话对节点逐次编码从而模拟语义推理过程,最终预测当前对话的答案实体,解决了对话中存在缺省词和指代词的问题以及复杂语境下的特征提取问题.实验结果表明,该方法更关注实体间的关系,有助于保持推理的完整性和准确性,在一定程度上证明了将上下文建模为关系节点图的实用性和有效性.Based on a path reasoning method of graph encoder,we used the entity relationships between multi rounds of dialogue in the knowledge graph as a node graph.The encoder sequentially encoded the nodes according to each round of dialogue to simulate the semantic reasoning process,and utimately predicted the answer entity for the current dialogue.This approach solved the problems of missing words and pronouns in dialogues,as well as feature extraction problems in complex contexts.The experimental results show that the method focused more on the relationships between entities,which helped to maintain the integrity and accuracy of reasoning.To a certain extent,it proved the practicality and effectiveness of modeling context as a relational node graph.

关 键 词：知识图谱 自然语言处理 多轮问答 卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]