Named entity recognition

Named Entity Recognition (NER) automatically identifies words or phrases of a special meaning in texts and classifies them into groups (e.g. persons, organizations, products, dates, cities, coutnries, product names).

NER can be used in wide range of applications, e.g. in other NLP tasks such as Question Answering or Machine Translation to improve their results, in indexing to precisely find documents related to some person or organization, in sentiment analysis to link results to particular products.

Our research is focused on multilinual NER and our current system is at the world state-of-the-art level. We have also rich experiences and excelent results with Czech NER [Konkol and Konopík, 2013].


Jakub Piskorski and Laska Laskova and Michał Marcińczuk and Lidia Pivovarova and Pavel Přibáň and Josef Steinberger and Roman Yangarber
The Second Cross-Lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic Languages
Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing (2019)
Named entitity recognition
Michal Konkol
First Steps in Czech Entity Linking
Text, Speech, and Dialogue (2015)
BibTex | PDF
Named entitity recognition
Tomáš Brychcín and Michal Konkol and Josef Steinberger
UWB: Machine Learning Approach to Aspect-Based Sentiment Analysis
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) (2014)
BibTex | PDF
Semantic analysis | Sentiment analysis | Named entitity recognition
Pavel Král
Named entities as new features for Czech document classification
15th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2014) (2014)
BibTex | PDF
Named entitity recognition | Document classification
Back to Top