基于OWL的本体集成

提出一种新的本体集成方法。分析了本体集成的原因,阐述了本体集成时应遵循的4条基本原则,并给出了集成的分类,提出了一种基于OWL DL图闭包的本体集成方法。该方法将OWL DL本体抽象为RDFS图模型,根据给定的OWL DL推理规则生成OWL DL本体的图闭包,在此基础上进行本体集成,同时提出了几种计算实体相似度的方法,将本方法与COMA++和FCA-merge进行实验对比,本方法在准确率和召回率上占优势。     

细分曲面求交交线计算方法的研究

主要针对三角网格的细分曲面求交提出了一种有效的交线计算的方法,该方法适用于任意三角网格的细分曲面中.在利用AABB和二部图进行初始控制网格相交性检测后,利用该方法快速有效地求出细分曲面的交线.     

一种基于Web漏洞威胁模型的网站安全分析技术

网站日益受到黑客的青睐,针对Web应用程序的攻击事例屡见不鲜。如何全面、准确地分析网站面临的最大威胁成为专业信息安全公司和网站管理员的不可回避的难题。本论文借鉴攻击图的基本思想设计了漏洞威胁测试模型(VTTM),并以SQL注入漏洞为例对其进行建模,并利用两种算法分别计算了网站的最大威胁值及最优测试序列。     

From tabular data to knowledge graphs: A survey of semantic table interpretation tasks and methods

Tabular data often refers to data that is organized in a table with rows and columns. We observe that this data format is widely used on the Web and within enterprise data repositories. Tables potentially contain rich semantic information that still needs to be interpreted. The process of extracting meaningful information out of tabular data with respect to a semantic artefact, such as an ontology or a knowledge graph, is often referred to as Semantic Table Interpretation (STI) or Semantic Table Annotation. In this survey paper, we aim to provide a comprehensive and up-to-date state-of-the-art review of the different tasks and methods that have been proposed so far to perform STI. First, we propose a new categorization that reflects the heterogeneity of table types that one can encounter, revealing different challenges that need to be addressed. Next, we define five major sub-tasks that STI deals with even if the literature has mostly focused on three sub-tasks so far. We review and group the many approaches that have been proposed into three macro families and we discuss their performance and limitations with respect to the various datasets and benchmarks proposed by the community. Finally, we detail what are the remaining scientific barriers to be able to truly automatically interpret any type of tables that can be found in the wild Web.     

基于MFE-BERT与FNNAttention的心理医学知识图谱构建

针对心理医学领域文本段落冗长、数据稀疏、知识散乱且规范性差的问题, 提出一种基于多层级特征抽取能力预训练模型(MFE-BERT)与前向神经网络注意力机制(FNNAttention)的心理医学知识图谱构建方法. MFE-BERT在BERT模型基础上将其内部所有Encoder层特征进行合并输出, 以获取包含更多语义的特征向量, 同时对两复合模型采用FNNAttention机制强化词级关系, 解决长文本段落语义稀释问题. 在自建的心理医学数据集中, 设计MFE-BERT-BiLSTM-FNNAttention-CRF和MFE-BERT-CNN-FNNAttention复合神经网络模型分别进行心理医学实体识别和实体关系抽取, 实体识别F1值达到93.91%, 实体关系抽精确率达到了89.29%, 通过融合文本相似度与语义相似度方法进行实体对齐, 将所整理的数据存储在Neo4j图数据库中, 构建出一个含有3652个实体, 2396条关系的心理医学知识图谱. 实验结果表明, 在MFE-BERT模型与FNNAttention机制的基础上构建心理医学知识图谱切实可行, 提出的改进模型所搭建的心理医学知识图谱可以更好地应用于心理医学信息管理中, 为心理医学数据分析提供参考.     

APPCorp: a corpus for Android privacy policy document structure analysis

With the increasing popularity of mobile devices and the wide adoption of mobile Apps, an increasing concern of privacy issues is raised. Privacy policy is identified as a proper medium to indicate the legal terms, such as the general data protection regulation (GDPR), and to bind legal agreement between service providers and users. However, privacy policies are usually long and vague for end users to read and understand. It is thus important to be able to automatically analyze the document structures of privacy policies to assist user understanding. In this work we create a manually labelled corpus containing 231 privacy policies (of more than 566,000 words and 7,748 annotated paragraphs). We benchmark our data corpus with 3 document classification models and achieve more than 82% on F1-score.     

Few-shot node classification via local adaptive discriminant structure learning

Node classification has a wide range of application scenarios such as citation analysis and social network analysis. In many real-world attributed networks, a large portion of classes only contain limited labeled nodes. Most of the existing node classification methods cannot be used for few-shot node classification. To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples, in this paper, we propose a local adaptive discriminant structure learning (LADSL) method for few-shot node classification. LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlarging inter-class differences. Extensive experiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.     

Cold-Start Link Prediction via Weighted Symmetric Nonnegative Matrix Factorization with Graph Regularization

Link prediction has attracted wide attention among interdisciplinary researchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future networks. Despite the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connected graph. However, the complexity of the real world makes the complex networks abstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start link prediction is favored as one of the most valuable subproblems of traditional link prediction. However, due to the loss of many links in the observation network, the topological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topological information from observed network becomes the key point to solve the problem of cold-start link prediction. In this paper, we propose a framework for solving the cold-start link prediction problem, a joint-weighted symmetric nonnegative matrix factorization model fusing graph regularization information, based on low-rank approximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designed graph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain each other. Finally, a unified framework for implementing cold-start link prediction is constructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validation on five real networks with attributes shows that the proposed model has very good predictive performance when predicting missing edges of isolated nodes.     

基于有向图模型的旅游领域命名实体识别

旅游领域命名实体识别是旅游知识图谱构建过程中的关键步骤,与通用领域的实体相比,旅游文本的实体具有长度长、一词多义、嵌套严重的特点,导致命名实体识别准确率低。提出一种融合词典信息的有向图神经网络（L-CGNN）模型,用于旅游领域中的命名实体识别。将预训练词向量通过卷积神经网络提取丰富的字特征,利用词典构造句子的有向图,以生成邻接矩阵并融合字词信息,通过将包含局部特征的词向量和邻接矩阵输入图神经网络（GNN）中,提取全局语义信息,并引入条件随机场（CRF）得到最优的标签序列。实验结果表明,相比Lattice LSTM、ID-CNN+CRF、CRF等模型,L-CGNN模型在旅游和简历数据集上具有较高的识别准确率,其F1值分别达到86.86%和95.02%。     

基于改进多嵌入空间的实时语义数据流推理

将语义数据流处理引擎与知识图谱嵌入表示学习相结合,可以有效提高实时数据流推理查询性能,但是现有的知识表示学习模型更多关注静态知识图谱嵌入,忽略了知识图谱的动态特性,导致难以应用于实时动态语义数据流推理任务。为了使知识表示学习模型适应知识图谱的在线更新并能够应用于语义数据流引擎,建立一种基于改进多嵌入空间的动态知识图谱嵌入模型PUKALE。针对传递闭包等复杂推理场景,提出3种嵌入空间生成算法。为了在进行增量更新时更合理地选择嵌入空间,设计2种嵌入空间选择算法。基于上述算法实现PUKALE模型,并将其嵌入数据流推理引擎CSPARQL-engine中,以实现实时语义数据流推理查询。实验结果表明,与传统的CSPARQL和KALE推理相比,PUKALE模型的推理查询时间分别约降低85%和93%,其在支持动态图谱嵌入的同时能够提升实时语义数据流推理准确率。