ISWC2020 papers
From ISWC2020, an international conference on Semantic Web technology, one of the artificial intelligence technologies for handling knowledge information. In the previous article, we discussed ISWC2019.
The ISWC2020 was greatly enhanced by the presentation of the Knowledge Graph. The main contents are as follows
- Keeping Reality in check
The major issues of the Semantic Web (sharing common conceptualizations, system and web usability, knowledge engineering, reasoning) were discussed in terms of “Reality” in relation to real scenarios and observable social behaviors.
- Semantic Programming
As for Semantic Web programming, it primarily describes how knowledge graphs support and enhance developers and bring intelligence to various coding activities.
- Hybrid Knowledge Graph Ecosystem
The approach will be to use the ontology to improve the neural model or to use the neural model to improve the ontology. The limitations that Hybrid KG wants to overcome will be the challenges caused by the bias of the data that machine learning has and the challenges caused by the exceptions of local data, even if only in the knowledge representation. These would not only automate linking using ML, but would also leverage inference using KR to answer questions about the “why” of phenomena. Specific approaches include those that compute the transitive closure of graphs and then compute node embeddings for compound similarity, also using GPT-3 for biomedical text, or daisy-chaining BERT, LSTM, and CRF for NER and linkage. Papers include the following.
“AI-KG: an Automatically Generated Knowledge Graph of Artificial Intelligence.”
This paper introduces the Artificial Intelligence Knowledge Graph (AI-KG). It will be a large auto-generated knowledge graph describing 820K research entities. the AI-KG contains approximately 14M RDF triples and 1.2M modified statements extracted from 333K research publications in the field of AI, linked by 27 relations, 5 types of entities (e.g., tasks, methods, metrics, materials, etc.) AI-KG is designed to support a range of intelligent services to analyze and understand research dynamics, support researchers in their daily work, and inform the decision-making of funding agencies and research policy makers Designed AI-KG was generated by applying an automated pipeline to extract entities and relationships using three tools: DyGIE ++, Stanford CoreNLP, and the CSO classifier. The resulting triples were then merged and filtered using a combination of deep learning and semantic technologies to create a high-quality knowledge graph. This pipeline was evaluated against a manually created gold standard, yielding competitive results; AI-KG is available in CCBY 4.0 and can be downloaded as a dump or queried via the SPARQL endpoint.
- RML (RDF Mapping Language) is described
“Turning Transport Data into EU Compliance while Enabling a Multimodal Transport Knowledge Graph”, “Knowledge Graph Construction using Declarative Mapping Rules” and “How to build large knowledge graphs efficiently (LKGT)” and “Facilitating the Analysis of COVID-19 Literature Through a Knowledge Graph”The report included the following. These ontology matching technologies have also attracted attention as start-up technologies in the United States.
Workshop 11th Workshop on Ontology Design and Patterns (WOP 2020) 4th Workshop on Storing, Querying, and Benchmarking the Web of Data (QuWeDa 2020) The Semantic Web in Practice: Tools and Pedagogy (PRAXIS) 6th Workshop on Managing the Evolution and Preservation of the Data Web (MEPDaW 2020) 13th International Workshop on Scalable Semantic Web Knowledge Base Systems (SSWS2020) Third International Workshop on Semantic Web Meets Health Data Management (SWH 2020) Wikidata Workshop The Sixth International Workshop on Natural Language Interfaces for the Web of Data (NLIWOD) 7th International Workshop on Dataset PROFlLing and Search (PROFILES 2020) VOILA 2020 – 5th International Workshop on Visualization and Interaction for Ontologies and Linked Data International Workshop on Artificial Intelligence Technologies for Legal Documents (AI4LEGAL) The Fifteenth International Workshop on Ontology Matching (OM-2020) Semantics for Online Misinformation Detection, Monitoring, and Prediction First workshop on Research data* management for linked open science (DaMaLOS) Tutorial A Data Science Pipeline for Big Linked Earth Observation Data Scalable RDF Analytics with SANSA Knowledge Graph Construction using Declarative Mapping Rules Building Mobile Semantic Web Apps with Punya Pattern-based knowledge base construction (OTTR) SPARQL Endpoints and Web API (SWApi) Common Sense Knowledge Graphs (CSKGs) Semantic Explainability For All – SEMEX4ALL How to build large knowledge graphs efficiently (LKGT) Shapes applications and tools SESSION 1A: KNOWLEDGE REPRESENTATION AND REASONING OWL2Bench: A Benchmark for OWL 2 Reasoners (RS) Prevalence and Effects of Class Hierarchy Precompilation in Biomedical Ontologies (Research) Controlled Query Evaluation in Ontology-based Data Access (Research) SESSION 1B: KNOWLEDGE GRAPHS Refining Node Embeddings via Semantic Proximity (Research) Enriching Knowledge Bases with Interesting Negative Statements (SC) Covid-on-the-Web: Knowledge Graph and Services to Advance Covid-19 Research (RS) SESSION 1C: INFORMATION RETRIEVAL AND SEMANTIC ANALYSIS PreFace: Faceted Retrieval of Prerequisites using domain-specific Knowledge Bases (Research) Focused Query Expansion with Entity Cores for Patient-Centric Health Search (Research) Generating Referring Expressions from RDF Knowledge Graphs for Data Linking (Research) SESSION 1D: SCHOLARLY DATA The OpenCitations Data Model (In-Use) Linking ontological classes and archaeological forms (In-Use) AI-KG: an Automatically Generated Knowledge Graph of Artificial Intelligence (RS) SESSION 2A: SHACL SHACL Satisfiability and Containment (Research) Deciding SHACL Shape Containment through Description Logics Reasoning (Research) Domain-specific customization of schema.org based on SHACL (In-Use) SESSION 2B: KNOWLEDGE GRAPHS Crime event localization and deduplication (In-Use) Contextual Propagation of Properties for Knowledge Graphs: A Sentence Embedding Based Approach (Research) Explainable Link Prediction for Emerging Entities in Knowledge Graphs (Research) SESSION 2C: DATA MINING AND KNOWLEDGE-DRIVEN ML NABU – Multilingual Graph-based Neural RDF Verbalizer (Research) LM4KG: Improving Common Sense Knowledge Graphs with Language Models Enhancing Online Knowledge Graph Population with Semantic Knowledge SESSION 2D: PROGRAMMING THE SEMANTIC WEB The International Data Spaces Information Model – An Ontology for Sovereign Exchange of Digital Content (RS) LDflex: a Read/Write Linked Data Abstraction for Front-End Web Developers (RS) In-database Analytics with Recursive SPARQL (Research) SESSION 3A: INFORMATION RETRIEVAL AND SEMANTIC ANALYSIS Google Dataset Search by the Numbers (In-Use) SESSION 3B: KNOWLEDGE GRAPHS Facilitating COVID-19 Meta-analysis Through a Literature Knowledge Graph (RS) The Virtual Knowledge Graph System Ontop (RS) KGTK: A Toolkit for Large Knowledge Graph Manipulation and Analysis (RS) SESSION 3C: KNOWLEDGE ENHANCED LEARNING Ontology-Enhanced Machine Learning: a Bosch Use Case of Welding Quality Monitoring (In-Use) NEO: A Tool for Taxonomy Enrichment with New Emerging Occupations (In-Use) Understanding Data Centers from Logs: Leveraging External Knowledge for Distant Supervision (In-Use) SESSION 3D: SEARCH, QUERY, INTEGRATION AND ANALYSIS OBA: An Ontology-Based Framework for Creating REST APIs for Knowledge Graphs (RS) Extending SPARQL with Similarity Joins (Research) Dynamic Faceted Search for Technical Support exploiting Induced Knowledge (In-Use) SESSION 4A: INFORMATION RETRIEVAL AND SEMANTIC ANALYSIS Generating Compact and Relaxable Answers to Keyword Queries over Knowledge Graphs (Research) KnowlyBERT – Hybrid Query Answering over Language Models and Knowledge Graphs (Research) Linked Credibility Reviews for Explainable Misinformation Detection (Research) SESSION 4B: DATA MINING AND KNOWLEDGE-DRIVEN ML Rule-Guided Graph Neural Networks for Recommender Systems (Research) BCRL: Long Text Friendly Knowledge Graph Representation Learning (Research) Weakly Supervised Short Text Categorization using World Knowledge (Research) SESSION 4C: QUERY, INTEGRATION AND ANALYSIS Schímatos: a SHACL-based Web-Form Generator for Knowledge Graph Editing (RS) Revealing Secrets in SPARQL Session Level (Research) Squirrel – Crawling RDF Knowledge Graphs on the Web (RS) SESSION 4D: DATA STREAMS HDGI: A Human Device Gesture Interaction Ontology for the Internet of Things (RS) A First Step Towards A Streaming Linked Data Life-Cycle (In-Use) Stream Reasoning Agents (SC) SESSION 5A: ONTOLOGY-BASED INTEGRATION AND EXCHANGE Tentris– A Tensor-Based Triple Store (Research) Tab2Know: Building a Knowledge Base from Scientific Tables (Research) FunMap: Efficient Execution of Functional Mappings for Scaled-Up Knowledge Graph Creation (Research) SESSION 5B: REASONING IN USE Assisting the RDF Annotation of a Digital Humanities Corpus using Case-Based Reasoning (In-Use) Reasoning Engine for Prescriptive Maintenance (In-Use) Computing Compliant Anonymisations of Quantified ABoxes w.r.t. EL Policies (Research) SESSION 5C: DATA MINING AND KNOWLEDGE-DRIVEN ML Fantastic Knowledge Graph Embeddings and How to Find the Right Space for Them (Research) Detecting Different Forms of Semantic Shifts in Word Embeddings via Paradigmatic and Syntagmatic Association Changes (Research) ExCut: Explainable Embedding-based Clustering over Knowledge Graphs (Research) SESSION 5D: KNOWLEDGE GRAPHS IN USE A Knowledge Graph for Assessing Agressive Tax Planning Strategies (In-Use) Turning Transport Data into EU Compliance while Enabling a Multimodal Transport Knowledge Graph (In-Use) Enhancing Public Procurement in the European Union through Constructing and Exploiting an Integrated Knowledge Graph (In-Use) SESSION 6A: SW CHALLENGE 1 // SMART Augmentation-based Answer Type Classification of the SMART dataset Semantic Answer Type Prediction Using BERT Two-stage Semantic Answer Type Prediction for QA using BERT and Class-Specificity Rewarding COALA – A Rule-Based Approach to Answer Type Prediction SESSION 6B: KNOWLEDGE DRIVEN NLP Leveraging Semantic Parsing for Relation Linking over Knowledge Bases. (Research) A Novel Path-based Entity Relatedness Measure for Efficient Collective Entity Linking. (Research) Leveraging Linguistic Linked Data for Cross-lingual Model Transfer in the Pharmaceutical Domain (In-Use) SESSION 6C: ONTOLOGY ENGINEERING Nanomine: A Knowledge Graph for Nanocomposite Materials Science (RS) Explanation Ontology: A Model of Explanations for User-Centered AI (RS) Revisiting Ontologies of Units of Measure for Harmonising Quantity Values – a Use Case (In-Use) SESSION 6D: INDUSTRY 1 A context-aware recommendation system for mobile devices (Industry) Semantic-based quality of service management for real-time WebRTC streaming service (Industry) An Unsupervised Framework for Semantics Driven Causal Explanations for Anomalies (Industry) Anu Question Answering System (Industry) Semantic ML for Manufacturing Monitoring at Bosch (Industry) SESSION 7A: SW CHALLENGE 2 // SEMTAB Generating conceptual subgraph from tabular data for knowledge graph matching (SSL team) LinkingPark: An integrated approach for Semantic Table Interpretation SESSION 7B: INDUSTRY Unscripted Conversation driven through Knowledge Graph (Industry) SemNav: How Rich Semantic Knowledge Can Guide Robot Navigation in Indoor Spaces (Industry) Using connected data to empower a financial services organization: Project Helix at UBS (Industry) Knowledge Graphs and Creative Applications (Industry) Adventures in the Art of Enterprise Artificial Intelligence Transformation (Industry) SESSION 7C: ONTOLOGY ENGINEERING An Ontology for the Materials Design Domain (RS) An SKOS-based Vocabulary on the Swift Programming Language (RS) Tough Tables: Carefully Benchmarking Semantic Table Annotators (RS) SESSION 7D: ROBUST AND SCALABLE MANAGEMENT OF SEMANTICS AND DATA HDTCat: let’s make HDT scale (RS) Adaptive Low-level Storage of Very Large Knowledge Graphs (SC) Cost- and Robustness-based Query Optimization for Triple Pattern Fragment Clients. (Research) SESSION 8A: SW CHALLENGE 1 // SMART A Methodology for Hierarchical Classification of Semantic Answer Types of Questions Hierarchical Contextualized Representation Models for Answer Type Prediction Fine and Ultra-File type Embeddings for Quesiton Answering Question Embeddings for Semantic Answer Type Prediction SESSION 8B: SW CHALLENGE 2 // SEMTAB MTab4Wikidata at the SemTab 2020: Tabular Data Annotation with Wikidata DAGOBAH: Enhanced Scoring Algorithms for Scalable Annotations of Tabular Data MantisTable SE: an enhanced and efficient approach to a complete Semantic Table Interpretation SESSION 8C: SW CHALLENGE 3 // MINING ISCAS_ICIP at MWPD-2020 Task 1: Product Matching Based on Deep Entity Matching Frameworks Language Model CNN-driven Similarity Matching and Classification for HTML-embedded Product Data (TASK 1) Language Model CNN-driven Similarity Matching and Classification for HTML-embedded Product Data (TASK 2) SESSION 9A: SW CHALLENGE 3 // MINING PMap: Ensemble Pre-training Models for Product Matching (TASK 1 Winner) Bert with Dynamic Masked Softmax and Pseudo Labeling for Hierarchical Product Classification (TASK 2 Winner) SESSION 9B: MACHINE LEARNING FOR THE SEMANTIC WEB Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs (SC) Multi-view Knowledge Graph Embedding for Entity Alignment (SC) Learning Triple Embeddings from Knowledge Graphs (SC) SESSION 9C: DATA MINING AND KNOWLEDGE-DRIVEN ML From syntactic structure to semantic relationship: hypernym extraction from definitions by recurrent neural networks using the part of speech information. (Research) Learning Short-term Differences and Long-term Dependencies for Entity Alignment (Research) Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition. (Research) SESSION 9D: ONTOLOGY MAPPING, MERGING, AND ALIGNMENT G2GML: Graph to Graph Mapping Language for Bridging RDF and Property Graphs (RS) Generating Expressive Correspondences: An Approach based on User Knowledge Needs and A-box Relation Discovery (Research) Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules (SC) SESSION 10A: OPEN DATA ODArchive – Creating an archive for structured data from Open Data Portals (RS) Transparent Integration and Sharing of Life Cycle Sustainability Data with Provenance (In-Use)spotlight paperpartially reproduced GeoSPARQL+: Syntax, Semantics and System for Integrated Querying of Graph, Raster and Vector Data. (Research) SESSION 10B: QUESTION ANSWERING CASQAD – A New Dataset For Context-aware Spatial Question Answering (RS) RuBQ: A Russian Dataset for Question Answering over Wikidata (RS) PNEL: Pointer Network based End-To-End Entity Linking over Knowledge Graphs. (Research) SESSION 10C: INDUSTRY 3 ONE Record: One Step Closer to Digital Cargo with Ontologies and Linked Data (Industry) Knowledge-Based Approach for Structuring Cyclic ML Pipelines in the O&G Industry (Industry) An ontology for Maritime Situational Awareness Heterogeneous Sensor Networks (Industry) Knowledge Graphs for Workforce Reskilling Guidance (Industry) A Digital Buildings Ontology for Google’s Real Estate (Industry) SESSION 10D: IN-USE APPLICATIONS A Semantic Framework for Enabling Radio Spectrum Policy Management and Evaluation (In-Use) AWARE: A Situational Awareness Framework for Facilitating Adaptive Behavior of Autonomous Vehicles in Manufacturing (In-Use) Semantic Integration of Bosch Manufacturing Data Using Virtual Knowledge Graphs (In-Use)
In the next article, we will discuss ISWC0221.
コメント