• Publications
  • Influence
WebIsALOD: Providing Hypernymy Relations Extracted from the Web as Linked Open Data
TLDR
WebIsALOD is introduced, a Linked Open Data release of the IsA database, containing 400M hypernymy relations, each provided with rich provenance information, and runs a machine learning algorithm to assign confidence scores to the individual statements.
DOME results for OAEI 2018
TLDR
DOME (Deep Ontology MatchEr) is a scalable matcher which relies on large texts describing the ontological concepts to train a fixed-length vector representation of the concepts using the doc2vec approach.
WikiMatch - using Wikipedia for ontology matching
Finding correspondences between different ontologies is a crucial task in the Semantic Web. Ontology matching tools are capable of solving that task in an automated manner, some even dealing with
Towards Evaluating Interactive Ontology Matching Tools
TLDR
A number of quality measures for interactive ontology matching tools are introduced, and means to automatically run benchmark tests for such tools are discussed, to demonstrate how those evaluation can be designed.
DBkWik: A Consolidated Knowledge Graph from Thousands of Wikis
TLDR
This paper shows how to create one consolidated knowledge graph, called DBkWik, from thousands of Wikis, and shows that the resulting large-scale knowledge graph is complementary to DBpedia.
DBkWik: Towards Knowledge Graph Creation from Thousands of Wikis
TLDR
This paper shows how the DBpedia approach can be transferred to Fandom to create DBkWik, a complementary knowledge graph.
HotMatch results for OEAI 2012
HotMatch is a multi-strategy matcher developed by a group of students at Technische Universitat Darmstadt in the course of a hands-on training. It implements various matching strategies. The tool
Hertuda results for OEAI 2012
Hertuda is a very simple element based matcher. It shows that tokenization and a string measure can also yield in good results. It is an improved version of the first version submitted to the OAEI
Discoverability of SPARQL Endpoints in Linked Open Data
TLDR
This paper provides a quantitative analysis on the automatic discoverability of SPARQL endpoints using different mechanisms.
Language-Agnostic Relation Extraction from Abstracts in Wikis
TLDR
A language-agnostic approach that exploits background knowledge from the graph instead of language-specific techniques and builds machine learning models only from language-independent features is presented.
...
1
2
3
4
...