融入三维语义特征的常识推理问答方法  

Commonsense reasoning and question answering method with three-dimensional semantic features

作　　者：王红斌[1,2,3] 房晓[1,2,3] 江虹 WANG Hongbin;FANG Xiao;JIANG Hong(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming Yunnan 650500,China;Yunnan Key Laboratory of Artificial Intelligence(Kunming University of Science and Technology),Kunming Yunnan 650500,China;Yunnan Key Laboratory of Computer Technology Application(Kunming University of Science and Technology),Kunming Yunnan 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500 [2]云南省人工智能重点实验室(昆明理工大学),昆明650500 [3]云南省计算机技术应用重点实验室(昆明理工大学),昆明650500

出　　处：《计算机应用》2024年第1期138-144,共7页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61966020);云南省基础研究计划项目(202201AT070157)。

摘　　要：现有使用预训练语言模型和知识图谱的常识问答方法主要集中于构建知识图谱子图及跨模态信息结合的研究,忽略了知识图谱自身丰富的语义特征,且缺少对不同问答任务的知识图谱子图节点相关性的动态调整,导致预测准确率低。为解决以上问题,提出一种融入三维语义特征的常识推理问答方法。首先提出知识图谱节点的关系层级、实体层级、三元组层级三维语义特征量化指标;其次,通过注意力机制动态计算关系层级、实体层级、三元组层级三种维度的语义特征对不同实体节点间的重要性;最后,通过图神经网络进行多层聚合迭代嵌入三维语义特征,获得更多的外推知识表示,更新知识图谱子图节点表示,提升答案预测精度。与QA-GNN常识问答推理方法相比,所提方法在CommonsenseQA数据集上的验证集和测试集的准确率分别提高了1.70个百分点和0.74个百分点,在OpenBookQA数据集上使用AristoRoBERTa数据处理方法的准确率提高了1.13个百分点。实验结果表明,所提出的融入三维语义特征的常识推理问答方法能够有效提高常识问答任务准确率。The existing commonsense question answering methods based on pre-trained language model and knowledge graph mainly focus on the construction of subgraphs of knowledge graph and combination of cross-modal information,ignoring the rich semantic features of knowledge graph itself,and lack dynamic adjustment of correlation among knowledge graph subgraph nodes to different question answering tasks,thus they do not achieve satisfactory prediction accuracies.To solve these above problems,a commonsense reasoning and question answering method integrating three-dimensional semantic features was proposed.Firstly,the quantitative indicators of three-dimensional semantic features at relation level,entity level and triple level for knowledge graph nodes were proposed.Secondly,the importance of semantic features of three dimensions of relation level,entity level and triple level to different entity nodes was dynamically calculated through attention mechanism.Finally,multi-layer aggregation iterative embedding of three-dimensional semantic features was carried out through graph neural network,to obtain more extrapolated knowledge representation,update subgraph node representation of knowledge graph,and improve the accuracy of answer prediction.Compared with QA-GNN commonsense question answering and reasoning method,the accuracy of proposed method in verification set and test set of CommonsenseQA dataset was improved by 1.70 percentage points and 0.74 percentage points,and the accuracy of the proposed method by AristoRoBERTa data processing method on OpenBookQA dataset was improved by 1.13 percentage points.Experimental results show that the proposed commonsense reasoning and question answering method integrating three-dimensional semantic features can effectively improve the accuracy of commonsense question answering tasks.

关 键 词：常识问答 知识图谱 图神经网络 语义特征 注意力机制 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]