Linked Data and Knowledge Graphs in Large Organisations

Dear Colleagues,

Knowledge graphs are large networks of entities, their semantic types, properties, and the relationships that interrelate such entities over various topical domains. Through the explicit representation of knowledge in well-formed ways, knowledge graphs provide expressive and actionable descriptions of the domain of interest and support logical explanations of reasoning outcomes based on the context of an entity according to the graph.

Knowledge graphs have proved to be a powerful technology across different areas of artificial intelligence, including e.g. natural language processing and the semantic web, and have been adopted by industry for different purposes, including semantic search, automated fraud detection, intelligent chatbots, advanced drug discovery, dynamic risk analysis, content-based recommendation and knowledge management systems, to name but a few. It is no surprise that knowledge graphs were featured in Gartner’s 2018 Hype Cycle as one of the emerging technologies in AI.

However, despite the success of public knowledge graphs, like DBpedia or Wikidata, or corporate ones, like Google’s KG, knowledge graphs still face important challenges for widespread adoption by large and medium enterprises, which involve not only technical aspects but also social ones. Among them, we highlight: i) addressing coverage, freshness and correctness at a scale of billions of entities and assertions; ii) Identity management, linkage and entity unification (“are these two products the same?”); iii) interoperability and distributed ownership (80% of enterprise knowledge is locked in silos); iv) change and long-term evolution; and v) sharing and reuse of common parts of knowledge graphs amongst organizations.

We invite authors to submit original articles addressing these and other challenges related to knowledge graphs. To this purpose we offer four different types of submissions: i) research papers, including reproducible experiments; ii) reports from the trenches, i.e. in-use experiences, challenges and lessons learnt; iii) survey papers; and iv) blue sky ideas. While the first three are full-length papers of 30 pages max, submissions of the latter type must not exceed 12 pages.

For illustrative purposes, below we provide a list of possible topics, which are neither exhaustive nor mutually exclusive. We particularly welcome interdisciplinary research over multiple topics, as reflected by our Guest Editorial Board, which includes members from both academia and industry.

Dr. Jose Manuel Gomez-Perez
Dr. Jeff Z. Pan
Dr. Panos Alexopoulos
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Addressing coverage, freshness and correctness at scale in knowledge graphs
• Novel techniques and algorithms for automatic knowledge graph construction
• Crowdsourcing and human-in-the-loop knowledge graph construction
• Knowledge graph curation and interlinking
• Quality management in knowledge graphs
• Identity management and entity resolution in knowledge graphs
• Managing change, evolution, versioning and the semantic drift in knowledge graphs
• Knowledge graph reasoning and query answering
• Non-Boolean phenomena (uncertainty, vagueness, subjectivity) and truth management in knowledge graphs
• Multi-modal knowledge graphs (text, video, images and other media)
• Knowledge graph embedding, (sub)word, sense and joint word-sense embedding and their applications to knowledge graphs (completion, curation, reasoning, alignment)
• Sharing and reusing (parts of) knowledge graphs across organizations
• Data governance models for knowledge graphs in different types of organizations
• Knowledge graphs in information retrieval, including vertical and enterprise search
• Knowledge graphs in (multilingual) NLP for classification, question answering, sentiment analysis, and recognizing textual entailment
• Managing privacy and ethics in knowledge graphs
• Applications both in vertical domains and horizontal scenarios
• Experiences, reality checks, good and bad practices, lessons learned, measurable impact of the value added through knowledge graphs
• Blue-sky ideas and visions of the future of knowledge graphs