First Steps in Czech Entity Linking

Michal Konkol
Text, Speech, and Dialogue (2015)


Research topics:

Named Entity Recognition


In this paper, we present our approach for a simplified Entity Linking task in Czech, where entity mentions found in text are linked to a list of known entities. We evaluate both known and newly proposed methods for entity names similarity on a manually annotated newspaper corpus. We show that it is possible to achieve a very high accuracy in this task, which is required in many natural language processing tasks as well as in the commercial practice.



@incollection{jbibtex-1, year = {2015}, isbn = {978-3-319-24032-9}, booktitle = {Text, Speech, and Dialogue}, volume = {9302}, series = {Lecture Notes in Computer Science}, editor = {Král, Pavel and Matoušek, Václav}, doi = {10.1007/978-3-319-24033-6_55}, title = {First Steps in Czech Entity Linking}, url = {}, publisher = {Springer International Publishing}, keywords = {Entity linking; Named entity; Named entity disambiguation; Czech}, author = {Konkol, Michal}, pages = {489-496}, language = {English} }
Back to Top