@article{WaitelonisJuergesSack2019, author = {Waitelonis, J{\"o}rg and J{\"u}rges, Henrik and Sack, Harald}, title = {Remixing entity linking evaluation datasets for focused benchmarking}, series = {Semantic Web}, volume = {10}, journal = {Semantic Web}, number = {2}, publisher = {IOS Press}, address = {Amsterdam}, issn = {1570-0844}, doi = {10.3233/SW-180334}, pages = {385 -- 412}, year = {2019}, abstract = {In recent years, named entity linking (NEL) tools were primarily developed in terms of a general approach, whereas today numerous tools are focusing on specific domains such as e.g. the mapping of persons and organizations only, or the annotation of locations or events in microposts. However, the available benchmark datasets necessary for the evaluation of NEL tools do not reflect this focalizing trend. We have analyzed the evaluation process applied in the NEL benchmarking framework GERBIL [in: Proceedings of the 24th International Conference on World Wide Web (WWW'15), International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, 2015, pp. 1133-1143, Semantic Web 9(5) (2018), 605-625] and all its benchmark datasets. Based on these insights we have extended the GERBIL framework to enable a more fine grained evaluation and in depth analysis of the available benchmark datasets with respect to different emphases. This paper presents the implementation of an adaptive filter for arbitrary entities and customized benchmark creation as well as the automated determination of typical NEL benchmark dataset properties, such as the extent of content-related ambiguity and diversity. These properties are integrated on different levels, which also enables to tailor customized new datasets out of the existing ones by remixing documents based on desired emphases. Besides a new system library to enrich provided NIF [in: International Semantic Web Conference (ISWC'13), Lecture Notes in Computer Science, Vol. 8219, Springer, Berlin, Heidelberg, 2013, pp. 98-113] datasets with statistical information, best practices for dataset remixing are presented, and an in depth analysis of the performance of entity linking systems on special focus datasets is presented.}, language = {en} }