The First Cross-Lingual Challenge on Recognition, Normalization and Matching of Named Entities in Slavic Languages

摘要

This paper describes the outcomes of the First Multilingual Named Entity Challenge in Slavic Languages. The Challenge targets recognizing mentions of named entities in web documents, their normal-ization/lemmatization, and cross-lingual matching. The Challenge was organized in the context of the 6th Balto-Slavic Natural Language Processing Workshop, co-located with the EACL-2017 conference. Eleven teams registered for the evaluation, two of which submitted results on schedule, due to the complexity of the tasks and short time available for elaborating a solution. The reported evaluation figures reflect the relatively higher level of complexity of named entity tasks in the context of Slavic languages. Since the Challenge extends beyond the date of the publication of this paper, updates to the results of the participating systems can be found on the official web page of the Challenge.