Research & Innovation

Nathan Fulton

Managing connections between types and individuals is a crucial aspect of applied ontology, and effective scaling is one aspect of the challenge. At Indeed, we help people get jobs. In order to do this, we need to understand jobseekers’ qualifications and the requirements of jobs they search for. Millions of jobs and job seekers are connected to our system on any given day, however, and they could not possibly all be included in a single accurate and efficient knowledge graph.

Fortunately, a lot of common-sense general reasoning is about types of things. Our taxonomies and ontology form a graph of types, which are used to apply metadata to documents at scale. We also leverage meta-types and type-type relationships in order to provide the most sophisticated and accurate metadata. In implementing these solutions, we take advantage of a useful ambiguity: in the SKOS (Simple Knowledge Organization System) standard, a “Concept” is syntactically an individual, but most concepts seem to have semantic uses as types. This talk will discuss how using skos:Concept for first-order types and rdfs:Class for meta-types enables automated reasoning patterns and dynamic application behavior without any need for a knowledge graph of individuals.

Coding da VinciIT-Gruppe GeisteswissenschaftenInstitut für KunstgeschichteMunicResearch

Coding da Vinci is the first German open cultural data hackathon. Founded in Berlin in 2014, Coding da Vinci brings cultural heritage institutions together with the hacker & designer community to develop ideas and prototypes for the cultural sector and for the public.

Florian SchrageNicolas Heist

Knowledge Graph completion deals with the addition of missing facts to knowledge graphs. While quite a few approaches exist for type and link prediction in knowledge graphs, the addition of literal values (also called instance or entity attributes) is not very well covered in the literature.

Harshvardhan J. PanditDeclan O’SullivanDave Lewis

An organisation using personal data should document its data governance processes to maintain and demonstrate compliance with the General Data Protection Regulation (GDPR). As processes evolve, their documentation should reflect these changes with an assessment showing ongoing compliance.

Maria KoutrakiFarshad Bakhshandegan-MoghaddamHarald Sack

Natural language understanding tasks are key to extracting structured and semantic information from text. One of the most chal- lenging problems in natural language is ambiguity and resolving such ambiguity based on context including temporal information. This paper, focuses on the task of extracting temporal roles from text, e.g. CEO of an organization or head of a country.

Sebastian NeumaierVadim SavenkovAxel Polleres

In the past years Open Data has become a trend among governments to increase transparency and public engagement by opening up national, regional, and local datasets. However, while many of these datasets come in semi-structured file formats, they use different schemata and lack geo-references or semantically meaningful links and descriptions of the corresponding geo-entities.

Harshvardhan Jitendra PanditDeclan O’SullivanDave Lewis

Information associated with regulatory compliance is often siloed as legal documentation that is not suitable for querying or reuse. Utilising open standards and technologies to represent and query this information can facilitate interoperability between stakeholders and assist in the task of maintaining as well as demonstrating compliance.

Giuseppe FutiaAntonio VetròAlessio MelandriJuan Carlos De Martin

Knowledge graphs are labeled and directed multi-graphs that encode information in the form of entities and relationships. They are gaining attention in different areas of computer science: from the improvement of search engines to the development of virtual personal assistants.

Vincent LullyPhilippe LaubletMilan StankovicFilip Radulovic

Recommender systems are becoming must-have facilities on e-commerce websites to alleviate information overload and to improve user experience. One important component of such systems is the explanations of the recommendations.

Vincent LullyPhilippe LaubletMilan StankovicFilip Radulovic

In this paper, we explore the synergy between knowledge graph technologies and computer vision tools for personalisation systems. We propose two image user profiling approaches which map an image to knowledge graph entities representing the interests of a user who appreciates the image. The first one maps an image to entities which correspond to the objects appearing in the image.


Subscribe to RSS - Research & Innovation