Call for papers for special issue Information Fusion on “Knowledge Graph for Information Fusion”
摘要截稿:
全文截稿: 2020-01-05
影响因子: 13.669
期刊难度:
CCF分类: 无
中科院JCR分区:
• 大类 : 计算机科学 - 1区
• 小类 : 计算机:人工智能 - 1区
• 小类 : 计算机:理论方法 - 1区
Overview
Recently, knowledge graph (KG) is the graph-driven representation of real-world entities along with their semantic attributes and their relationships. Over the past few years, we have observed the emerging of many state-of-the-art knowledge graphs, some of which are Cyc and OpenCyc, Freebase, DBpedia, Wikidata, YAGO, and NELL. However, standalone knowledge graphs are of no use unless we integrate them into smart systems. In several well-known industrial services (e.g., Google’s Knowledge Graph, Microsoft’s Satori, and Facebook’s Graph Search), knowledge graph became a backbone for helping these organizations as well as their users fully discovering social knowledge. Particularly, these systems are able to provide hyper-precise information in various applications (e.g., semantic search engine, complex question answering, and users’ behavior comprehension). Regarding the importance of smart systems with knowledge graph, an increasing presence of innovative researches have been recognized to tackle different kinds of industrial domains.
Our main goal is to look for high-quality researches that focus on both theoretical papers and practical applications of knowledge graph. In particular, this special issue aims at gathering advanced researches to support constructing state-of-the-art smart systems with knowledge graph, including two main topics of interest: (1) cutting-edge techniques for constructing, managing, and analyzing knowledge graph ensuring its coverage, correctness, and freshness and (2) useful applications of knowledge graph for providing our society with prominent services.
Potential topics include, but are not limited to:
Construction, management, and analysis of knowledge graph:
• Automatic and semi-automatic knowledge graph construction.
• Knowledge graph identification (completion, reasoning, or refinement).
• Knowledge graph expansion and enrichment.
• Knowledge graph embedding.
• Knowledge graph understanding and profiling.
• Knowledge graph fusion.
• Real-time updating knowledge graph.
• Storing and querying knowledge graph.
• Visualizing knowledge graph.
• Deep learning for knowledge graph.
Applications of knowledge graph:
• Cross-lingual semantic search and ranking.
• Autonomous question answering.
• Social event detection and disambiguation.
• Explainable recommendation systems.
• Multi-lingual sentiment analysis.
• Large-scale text retrieval, analysis and understanding.
• Entity resolution and link prediction.
• Automated knowledge representation, inference, and reasoning.
• Spatio-temporal pattern discovery.
• Real-time edge analytics.
• Knowledge-based trust, fraud detection, and cybersecurity.