International Research School in Artificial Intelligence in Bergen最新文献

Knowledge Graphs: A Guided Tour (Invited Paper) 知识图谱:导览(特邀论文)

International Research School in Artificial Intelligence in Bergen Pub Date : 1900-01-01 DOI: 10.4230/OASIcs.AIB.2022.1

A. Hogan

引用次数: 2

Automating Moral Reasoning (Invited Paper) 自动化道德推理(特邀论文)

International Research School in Artificial Intelligence in Bergen Pub Date : 1900-01-01 DOI: 10.4230/OASIcs.AIB.2022.6

M. Slavkovik

引用次数: 0

Reasoning in Knowledge Graphs (Invited Paper) 知识图中的推理(特邀论文)

International Research School in Artificial Intelligence in Bergen Pub Date : 1900-01-01 DOI: 10.4230/OASIcs.AIB.2022.2

Ricardo Guimarães, A. Ozaki

引用次数: 0

Integrating Ontologies and Vector Space Embeddings Using Conceptual Spaces (Invited Paper) 利用概念空间集成本体和向量空间嵌入(特邀论文)

International Research School in Artificial Intelligence in Bergen Pub Date : 1900-01-01 DOI: 10.4230/OASIcs.AIB.2022.3

Zied Bouraoui, Víctor Gutiérrez-Basulto, S. Schockaert

{"title":"Integrating Ontologies and Vector Space Embeddings Using Conceptual Spaces (Invited Paper)","authors":"Zied Bouraoui, Víctor Gutiérrez-Basulto, S. Schockaert","doi":"10.4230/OASIcs.AIB.2022.3","DOIUrl":"https://doi.org/10.4230/OASIcs.AIB.2022.3","url":null,"abstract":"Ontologies and vector space embeddings are among the most popular frameworks for encoding conceptual knowledge. Ontologies excel at capturing the logical dependencies between concepts in a precise and clearly defined way. Vector space embeddings excel at modelling similarity and analogy. Given these complementary strengths, there is a clear need for frameworks that can combine the best of both worlds. In this paper, we present an overview of our recent work in this area. We first discuss the theory of conceptual spaces, which was proposed in the 1990s by Gärdenfors as an intermediate representation layer in between embeddings and symbolic knowledge bases. We particularly focus on a number of recent strategies for learning conceptual space representations from data. Next, building on the idea of conceptual spaces, we discuss approaches where relational knowledge is modelled in terms of geometric constraints. Such approaches aim at a tight integration of symbolic and geometric representations, which unfortunately comes with a number of limitations. For this reason, we finally also discuss methods in which similarity, and other forms of conceptual relatedness, are derived from vector space embeddings and subsequently used to support flexible forms of reasoning with ontologies, thus enabling a looser integration between embeddings and symbolic knowledge.","PeriodicalId":110801,"journal":{"name":"International Research School in Artificial Intelligence in Bergen","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134172010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Learning and Reasoning with Graph Data: Neural and Statistical-Relational Approaches (Invited Paper) 图数据的学习和推理:神经和统计关系方法(特邀论文)

International Research School in Artificial Intelligence in Bergen Pub Date : 1900-01-01 DOI: 10.4230/OASIcs.AIB.2022.5

M. Jaeger

{"title":"Learning and Reasoning with Graph Data: Neural and Statistical-Relational Approaches (Invited Paper)","authors":"M. Jaeger","doi":"10.4230/OASIcs.AIB.2022.5","DOIUrl":"https://doi.org/10.4230/OASIcs.AIB.2022.5","url":null,"abstract":"Graph neural networks (GNNs) have emerged in recent years as a very powerful and popular modeling tool for graph and network data. Though much of the work on GNNs has focused on graphs with a single edge relation, they have also been adapted to multi-relational graphs, including knowledge graphs. In such multi-relational domains, the objectives and possible applications of GNNs become quite similar to what for many years has been investigated and developed in the field of statistical relational learning (SRL). This article first gives a brief overview of the main features of GNN and SRL approaches to learning and reasoning with graph data. It analyzes then in more detail their commonalities and differences with respect to semantics, representation, parameterization, interpretability, and flexibility. A particular focus will be on relational Bayesian networks (RBNs) as the SRL framework that is most closely related to GNNs. We show how common GNN architectures can be directly encoded as RBNs, thus enabling the direct integration of “low level” neural model components with the “high level” symbolic representation and flexible inference capabilities of SRL. 2012 ACM Subject Classification Computing methodologies → Logical and relational learning; Computing methodologies → Neural networks","PeriodicalId":110801,"journal":{"name":"International Research School in Artificial Intelligence in Bergen","volume":"32 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113995812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Combining Embeddings and Rules for Fact Prediction (Invited Paper) 结合嵌入和规则的事实预测(特邀论文)

International Research School in Artificial Intelligence in Bergen Pub Date : 1900-01-01 DOI: 10.4230/OASIcs.AIB.2022.4

Armand Boschin, Nitisha Jain, Gurami Keretchashvili, Fabian M. Suchanek

引用次数: 2