QA-KGNet:一种语言模型驱动的知识图谱问答模型  

QA-KGNet: Language Model-driven Knowledge Graph Question-answering Model

作　　者：乔少杰 杨国平 于泳 韩楠[3] 覃晓 屈露露 冉黎琼 李贺 QIAO Shao-Jie;YANG Guo-Ping;YU Yong;HAN Nan;QIN Xiao;QU Lu-Lu;RAN Li-Qiong;LI He(School of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China;Digital Media Art Key Laboratory of Sichuan Province(Sichuan Conservatory of Music),Chengdu 610021,China;School of Management,Chengdu University of Information Technology,Chengdu 610225,China;Guangxi Key Lab of Human-machine Interaction and Intelligent Decision(Nanning Normal University),Nanning 530100,China;School of Computer Science and Technology,Xidian University,Xi’an 710071,China)

机构地区：[1]成都信息工程大学软件工程学院,四川成都610225 [2]数字媒体艺术四川省重点实验室(四川音乐学院),四川成都610021 [3]成都信息工程大学管理学院,四川成都610225 [4]广西人机交互与智能决策重点实验室(南宁师范大学),广西南宁530100 [5]西安电子科技大学计算机科学与技术学院,陕西西安710071

出　　处：《软件学报》2023年第10期4584-4600,共17页Journal of Software

基　　金：国家自然科学基金(61962006);四川省科技计划(2021JDJQ0021,2022YFG0186);四川音乐学院数字媒体艺术四川省重点实验室资助项目(21DMAKL02);成都市技术创新研发项目(2021-YF05-00491-SN);成都市重大科技创新项目(2021-YF08-00156-GX);成都市“揭榜挂帅”科技项目(2021-JB00-00025-GX);成都市软科学研究项目(2021-RK00-00065-ZF,2021-RK00-00066-ZF);广西重大创新驱动项目(桂科AA22068057);四川省社会科学高水平团队项目(2015Z177)。

摘　　要：基于知识图谱的问答系统可以解析用户问题,已成为一种检索知识、自动回答所询问题的有效途径.知识图谱问答系统通常是利用神经程序归纳模型,将自然语言问题转化为逻辑形式,在知识图谱上执行该逻辑形式能够得到答案.然而,使用预训练语言模型和知识图谱的知识问答系统包含两个挑战:(1)给定问答(questionanswering, QA)上下文,需要从大型知识图谱(knowledge graph, KG)中识别相关知识;(2)对QA上下文和KG进行联合推理.基于此,提出一种语言模型驱动的知识图谱问答推理模型QA-KGNet,将QA上下文和KG连接起来形成一个工作图,使用语言模型计算给定QA上下文节点与KG节点的关联度,并使用多头图注意力网络更新节点表示.在Commonsense QA、OpenBookQA和Med QA-USMLE真实数据集上进行实验来评估QA-KGNet的性能,实验结果表明:QA-KGNet优于现有的基准模型,表现出优越的结构化推理能力.The question-answering system based on knowledge graphs can analyze user questions,and has become an effective way to retrieve relevant knowledge and automatically answer the given questions. The knowledge graph-based question-answering system usually uses a neural program induction model to convert natural language question into a logical form, and the answer can be obtained by executing the logical form on the knowledge graph. However, the knowledge question-answering system by using pre-trained language models and knowledge graphs involves two challenges: (1) given the QA (question-answering) context, relevant knowledge needs to be identified from a large KG (knowledge graph);(2) it isneeded to perform the joint reasoning on QA context and KG. Based on these challenges, a language model-driven knowledge graph question-answering model is proposed, which connects the QA context and KG to form a joint graph, and uses a language model to calculate the relevance of the given QA context nodes and KG nodes, and a multi-head graph attention network is employed to update the node representation. Extensive experiments on the CommonsenseQA, OpenBookQA and MedQA-USMLE real datasets are conducted to evaluate the performance of QA-KGNet and the experimental results show that QA-KGNet outperforms existing benchmark models and exhibits excellent structured reasoning capability.

关 键 词：知识图谱 预训练语言模型 QA上下文 多头图注意力网络 联合推理 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]