LEADER 11099nam 2200541 450 001 996483161703316 005 20231201231807.0 010 $a3-031-10983-X 035 $a(MiAaPQ)EBC7046589 035 $a(Au-PeEL)EBL7046589 035 $a(CKB)24267879200041 035 $a(PPN)26389732X 035 $a(EXLCZ)9924267879200041 100 $a20230103d2022 uy 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 00$aKnowledge science, engineering and management $e15th international conference, KSEM 2022, Singapore, August 6-8, 2022, proceedings, Part I /$fGerard Memmi [and four others] editors 210 1$aCham, Switzerland :$cSpringer,$d[2022] 210 4$d©2022 215 $a1 online resource (778 pages) 225 1 $aLecture notes in computer science ;$v13368 311 08$aPrint version: Memmi, Gerard Knowledge Science, Engineering and Management Cham : Springer International Publishing AG,c2022 9783031109829 320 $aIncludes bibliographical references and index. 327 $aIntro -- Preface -- Organizations -- Contents - Part I -- Contents - Part II -- Contents - Part III -- Knowledge Science with Learning and AI (KSLA) -- A Decoupled YOLOv5 with Deformable Convolution and Multi-scale Attention -- 1 Introduction -- 2 Related Work -- 3 Our Method -- 3.1 Decoupled Head -- 3.2 Deformable Convolution -- 3.3 Multi-scale Attention -- 4 Experiments -- 4.1 Data, Parameter Settings and Performance Metrics -- 4.2 Results -- 5 Conclusions -- References -- OTE: An Optimized Chinese Short Text Matching Algorithm Based on External Knowledge -- 1 Introduction -- 2 Related Work -- 2.1 Pre-trained Models -- 2.2 Data Augmentation -- 2.3 Multi-granularity Information -- 3 Model -- 3.1 Data Augmentation Model -- 3.2 Input Model -- 3.3 Semantic Information Transformer -- 3.4 Sentence Matching Layer -- 3.5 Relation Classifier Layer -- 4 Experiment -- 4.1 Experiment Dataset -- 4.2 Experiment Result -- 5 Conclusion -- References -- KIR: A Knowledge-Enhanced Interpretable Recommendation Method -- 1 Introduction -- 2 Related Work -- 3 Problem Description -- 4 Method -- 4.1 KIR Framework -- 4.2 Category Feature -- 4.3 Attention Mechanism -- 4.4 Building User Preferences -- 4.5 Learning Algorithm -- 5 Experiments and Results -- 5.1 Datasets and Experimental Settings -- 5.2 Results and Analysis -- 6 Conclusion -- References -- ICKEM: A Tool for Estimating One's Understanding of Conceptual Knowledge -- 1 Introduction -- 1.1 Procedural and Conceptual Knowledge -- 1.2 The Framework -- 2 Evaluate Familiarity Degree -- 2.1 Definition of Knowledge and Learning -- 2.2 Discriminate Learning Sessions -- 2.3 Capture the Text Learning Content -- 2.4 Calculate a Knowledge Point's Share -- 2.5 The Subject's State and Learning Method -- 2.6 A Knowledge Point's Learning History -- 2.7 Memory Retention of a Learning Experience. 327 $a2.8 Calculate the Familiarity Degree -- 3 Estimate Understanding Degree -- 3.1 Calculation of Understanding Degree -- 4 Discussion -- 4.1 Trade-Offs Between Different Methods -- 4.2 Privacy Issues -- 4.3 Analyzing with Topic Models -- 5 Related Work -- 6 Conclusion -- References -- Cross-perspective Graph Contrastive Learning -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Perspective-specific Convolution Module -- 3.2 Cross-perspective Contrastive Learning Module -- 3.3 Information Fusion Module -- 3.4 Optimization Objective -- 4 Experimental Analysis -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Parameters Setting -- 4.4 Node Classification Results -- 4.5 Ablation Study -- 4.6 Parameter Sensitivity -- 5 Conclusion -- References -- A Multi-scale Convolution and Gated Recurrent Unit Based Network for Limit Order Book Prediction -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Problem Formulation -- 3.2 Independent Feature Representation -- 3.3 Market State Representation -- 3.4 Feature Fusion -- 3.5 Temporal Attention Module -- 4 Experiments -- 4.1 Experiments Settings -- 4.2 Dataset -- 4.3 Results -- 5 Conclusion -- References -- Pre-train Unified Knowledge Graph Embedding with Ontology -- 1 Introduction -- 2 Related Work on Entity Typing Task -- 3 Background and Methodology -- 3.1 Rot-Pro Model -- 4 Method -- 4.1 Relation Patterns Within Each Layer -- 4.2 Relation Patterns Between Layers -- 4.3 Optimization Objective -- 5 Experiment -- 5.1 Datasets -- 5.2 Experimental Settings -- 5.3 Experimental Results -- 6 Conclusion -- References -- Improving Dialogue Generation with Commonsense Knowledge Fusion and Selection -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Task Formulation and Model Overview -- 3.2 Context Encoder -- 3.3 Knowledge-Enriched Encoder -- 3.4 Topic Fact Predictor -- 3.5 Response Generator. 327 $a4 Experiments -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Experimental Setup -- 4.4 Evaluation Metrics -- 4.5 Results and Analysis -- 5 Conclusion and Future Work -- References -- A Study of Event Multi-triple Extraction Methods Based on Edge-Enhanced Graph Convolution Networks -- 1 Introduction -- 2 Related Works -- 3 Proposed Approach -- 3.1 Indicator for Event Argument Detection Based on EE-GCN -- 3.2 Event Argument and Role Match Based on ACE2005 -- 3.3 Event Argument and Role Extraction Based on NER -- 3.4 Event Multi-triple Generation -- 4 Experimental Evaluation -- 4.1 Experimental Setup -- 4.2 Experimental Design -- 4.3 Generate Indicator for Event Argument Detection -- 4.4 Argument Extraction -- 4.5 Generate Event Multi-triple -- 5 Conclusion and Future Works -- References -- Construction Research and Applications of Industry Chain Knowledge Graphs -- 1 Introduction -- 2 Related Work -- 3 Construction Method of Industry Chain Knowledge Graph -- 3.1 Ontology Modeling of Knowledge Graphs in Financial Field -- 3.2 Knowledge Extraction Based on Dependency Parsing -- 3.3 Automatic Labeling and Named Entity Recognition -- 4 Experiment -- 5 Conclusion -- References -- Query and Neighbor-Aware Reasoning Based Multi-hop Question Answering over Knowledge Graph -- 1 Introduction -- 2 Related Work -- 2.1 Multi-hop KGQA -- 2.2 Attention in KGQA -- 2.3 GNN in KGQA -- 3 Methodology -- 3.1 Preliminary -- 3.2 Instruction Module and KG Initialization -- 3.3 CoAttention Module -- 3.4 Neighbor-Aware Reasoning -- 4 Experiment -- 4.1 Dataset -- 4.2 Implementation Details -- 4.3 Results and Analysis -- 4.4 Ablation Study -- 4.5 Influence of Parameters -- 4.6 Case Study -- 5 Conclusion -- References -- Question Answering over Knowledge Graphs with Query Path Generation -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 Related Definition. 327 $a3.2 The Framework of KGQA Based on Query Path Generation -- 4 Experimental Results and Analysis -- 4.1 Experimental Datasets -- 4.2 Baseline and Evaluation Metrics -- 4.3 Experimental Results and Analysis -- 4.4 Case Study -- 5 Conclusion -- References -- Improving Parking Occupancy Prediction in Poor Data Conditions Through Customization and Learning to Learn -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 The Model Training Module -- 3.2 The Model Pretraining Module -- 3.3 The Client Selection Module -- 4 Experiments and Results -- 4.1 Evaluation Preparation -- 4.2 Result and Discussions -- 5 Conclusions and Future Works -- References -- Knowledge Concept Recommender Based on Structure Enhanced Interaction Graph Neural Network -- 1 Introduction -- 2 Related Work -- 3 Preliminary -- 3.1 Problem Statement -- 3.2 Key Concept -- 4 Proposed Method -- 4.1 Entity Feature Extraction and Entity Relation Extraction -- 4.2 Knowledge Concept Representation Learning Based on Structure-Enhanced Interaction Graph Neural Network -- 4.3 User Representation Learning Based on Heterogeneous Graph Neural Network -- 4.4 Extended Matrix Factorization for Knowledge Concept Recommendation -- 5 Experiments -- 5.1 Dataset Description -- 5.2 Evaluation Metrics -- 5.3 Evaluation of Model Parameters -- 5.4 Baseline Methods -- 5.5 Experiment Setup -- 5.6 Results -- 6 Conclusion -- References -- Answering Complex Questions on Knowledge Graphs -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 Topic Entity Recognition -- 3.2 Core Path Generation -- 3.3 Constraints Selection -- 4 Experimental Studies -- 4.1 Settings -- 4.2 Model Training -- 4.3 Results and Analysis -- 5 Conclusion -- References -- Multi-attention User Information Based Graph Convolutional Networks for Explainable Recommendation -- 1 Introduction -- 2 Preliminaries -- 2.1 Foggy Feedback. 327 $a2.2 Knowledge Graph Integration -- 3 Methodology -- 3.1 KG Embedding Layer -- 3.2 Perceptual Bias Layer -- 3.3 Attention Characteristic Aggregation Layer -- 3.4 Prediction Layer -- 4 Experiments -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Experiments Setup -- 4.4 Performance Comparison -- 4.5 Specific Comparison -- 5 Conclusion and Future Work -- References -- Edge-Shared GraphSAGE: A New Method of Buffer Calculation for Parallel Management of Big Data Project Schedule -- 1 Introduction -- 2 Related Work -- 3 Background -- 3.1 Schedule Network -- 3.2 Critical Chain Method -- 3.3 Buffer Size -- 3.4 Evaluation Index -- 4 Edge-Shared GraphSAGE -- 4.1 Global Network Without Resource Sharing -- 4.2 Global Network with Resource Sharing -- 4.3 Features of the Node -- 4.4 Edge-Shared GraphSAGE -- 4.5 Calculate the Project Buffer and Import Buffer -- 5 Experiment -- 5.1 Data -- 5.2 Method -- 5.3 Comparison -- 6 Conclusion -- References -- Tackling Solitary Entities for Few-Shot Knowledge Graph Completion -- 1 Introduction -- 2 Preliminaries -- 3 Methodology -- 3.1 Local Pattern Graph Construction -- 3.2 Message Passing over Local Pattern Graph -- 3.3 HGAT for Encoding One-Hop Neighbors -- 3.4 Query-Aware Gating Mechanism -- 3.5 Transformer Relation Learner -- 3.6 Attentive Prototypical Network -- 3.7 Model Training -- 4 Experiments -- 4.1 Datasets and Baselines -- 4.2 Implementation Details -- 4.3 Main Results -- 4.4 Ablation Study -- 5 Conclusion -- References -- CP Tensor Factorization for Knowledge Graph Completion -- 1 Introduction -- 2 Related Work -- 3 Knowledge Graph Completion Based on CP Decomposition -- 3.1 Problem Definition -- 3.2 Model Definition -- 3.3 Model Learning -- 3.4 Model Analysis -- 4 Experiments and Results -- 4.1 Datasets -- 4.2 Implementation and Evaluation -- 4.3 Experiment Setting -- 4.4 Link Prediction Result -- 5 Conclusion. 327 $aReferences. 410 0$aLecture notes in computer science ;$v13368. 606 $aData mining 606 $aData mining$vCongresses 606 $aDecision making$xData processing 615 0$aData mining. 615 0$aData mining 615 0$aDecision making$xData processing. 676 $a006.312 702 $aMemmi$b Gerard 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a996483161703316 996 $aKnowledge Science, Engineering and Management$9772454 997 $aUNISA