Entity Linking is a common approach to information extraction in the context of unstructured text. One of the key challenges in entity linking is so called "Word Sense Disambiguation" where the meaning of a ambiguous word has to be determined (example: musical keyboard vs computer keyboard). To find unambiguous definitions of a word, knowledge graphs (e.g. Wikidata, DBpedia) are employed . Knowledge graphs identify and describe concepts in a structured manner.
Recent research of our group has proposed an interactive concept validation approach , to ensure the quality of the extracted information. Currently, this approach uses a specific hard-coded combination of knowledge graphs.
Propose a general model on how to integrate the interactive concept validation with different concept annotation services, for example Cyc , BabelNet , Yago . This includes
listing steps needed in the interactive concept validation
listing information queries (API) needed for these steps
modeling a general API for the ICV
implementing two backends for it (for example: existing approach + Cyc)
Understand the process of Entitiy Linking by reading .
Understand the ICV by reading  and analysing the current software.
List the information needed by ICV.
Analyse how to obtain the information needed from different knowledge bases (by using the knowledge graphs listed in )
Based on the analysis: propose a generalized model.
Implement two different backends, to validate the generalized model.
 Mackeprang, M., Khiat, A., & Müller-Birn, C. (2018, April). Concept Validation during Collaborative Ideation and Its Effect on Ideation Outcome. In Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems (p. LBW033). ACM.
 Martinez-Rodriguez, J., Aidan Hogan, and Ivan Lopez-Arevalo. "Information Extraction meets the Semantic Web: A Survey." Semantic Web journal (2018).
 Foxvog D. 2010. Cyc. Theory and Applications of Ontology: Computer Applications. :259-278.
 R. Navigli and S. Ponzetto. BabelNet: The Automatic Construction, Evaluation and Application of a Wide-Coverage Multilingual Semantic Network. Artificial Intelligence, 193, Elsevier, 2012, pp. 217-250
 Farzaneh Mahdisoltani, Joanna Biega, Fabian M. Suchanek YAGO3: A Knowledge Base from Multilingual Wikipedias (pdf) Conference on Innovative Data Systems Research (CIDR 2015).