基于学术知识图谱的辅助创新技术研究  

Academic Knowledge Graph-based Research for Auxiliary Innovation Technology

作　　者：钟将[1] 尹红 张剑 ZHONG Jiang;YIN Hong;ZHANG Jian(College of Computer Science,Chongqing University,Chongqing 400044,China;Chongqing Xixintianyuan Data Information Co.,Ltd.,Chongqing 401121,China)

机构地区：[1]重庆大学计算机学院,重庆400044 [2]重庆西信天元数据资讯有限公司,重庆401121

出　　处：《计算机科学》2022年第5期194-199,共6页Computer Science

基　　金：重庆市高等教育教学改革研究重大项目(191003);教育部新工科研究与实践项目(E-JSJRJ20201335)。

摘　　要：计算机领域知识快速更新且存在较多歧义,导致学生自主创新时难以找到合理的解决方案。作为辅助创新工具,智能问答系统可以协助学生更快地把握学科发展前沿,精准地找出解决问题的方法。在大规模科技文献库上构建科研知识图谱,实现了辅助学生创新的智能问答系统。为了减小查询问句中噪声实体带来的影响,提出一种基于辅助任务的意图信息增强神经网络(Auxiliary Task Enhanced Intent Information for Question Answering in Computer Domain,ATEI-QA)。相比传统方法,该方法能够更精确地提取问句意图信息,减小噪声实体给意图识别带来的影响。在计算机领域数据集和通用数据集上与3个主流模型开展了对比实验,结果表明所提模型在领域数据集上的MAP和MRR值平均提升了3.27%和1.72%,在通用数据集上的MAP和MRR值平均提升了4.37%和2.81%。Due to the rapid updating of computer knowledge with many ambiguities,it is difficult for students to seek reasonable solutions for independent innovation.As an auxiliary innovation tool,intelligent question-answering system can help students to grasp the frontier of subject development,find out solutions for problems faster and precisely.In this paper,a knowledge graph of scientific research is constructed based on a large-scale database of scientific and technological documents,which realizes an intelligent question answering system for assisting students in innovation.In order toreduce the influence of noisy entities on query questions,this paper proposes an auxiliary task enhanced intent information for question answering in computer domain(ATEI-QA).Compared with the traditional method,this method can extract the question intention information more accurately and further reduce the influence of noisy entity on intention recognition.Additionally,we conduct a series of experimental studies on computer and common datasets,and compare with three mainstream methods.Finally,experimental results demonstrate that our model achieves significant improvements against with three baselines,improving MAP and MRR scores by average of 3.27%,1.72%in the computer dataset and 4.37%,2.81%in the common dataset respectively.

关 键 词：智能问答 知识图谱 意图识别 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]