Study on Named Entity Recognition for Polish Based on Hidden Markov Models (2010)
Michał Marcińczuk and Maciej Piasecki (2010). "Study on Named Entity Recognition for Polish Based on Hidden Markov Models". In: Proceedings of the 13th International Conference on Text, Speech and Dialogue, Brno, Czech, 6–10 September 2010.
Abstract: Accuracy of a Named Entity Recognition algorithm based on the Hidden Markov Model is investigated. The algorithm was limited to recognition and classification of Named Entities representing persons. The algorithm was tested on two small Polish domain corpora of stock exchange and police reports. Comparison with the base lines algorithms based on the case of the first letter and a gazetteer is presented. The algorithm expressed 62% precision and 93% recall for the domain of the training data. Introduction of the simple hand-written post-processing rules increased precision up to 89%. We discuss also the problem of the method portability. A model of the combined knowledge sources is sketched also%in conclusions as a possible way to overcome the portability problem.
Keywords: Named Entity Recognition, Machine Learning, HiddenMarkov Model, Polish
Bibtex
@incollection {Marcinczuk:2010:tsd,
author = {Marci{\'n}czuk, Micha{\l} and Piasecki, Maciej},
affiliation = {Institute of Informatics, Wroc{\l}aw University of Technology, Wybrzeże Wyspia{\'n}skiego 27, Wroc{\l}aw, Poland},
title = {Study on Named Entity Recognition for Polish Based on Hidden Markov Models},
booktitle = {Text, Speech and Dialogue},
series = {Lecture Notes in Computer Science},
editor = {Sojka, Petr and Hor{\'a}k, Ale\v{s} and Kopecek, Ivan and Pala, Karel},
publisher = {Springer Berlin / Heidelberg},
isbn = {},
pages = {142-149},
volume = {6231},
url = {http://dx.doi.org/10.1007/978-3-642-15760-8\_19},
note = {10.1007/978-3-642-15760-8\_19},
year = {2010}
}
Poster
Study on Named Entity Recognition for Polish Based on Hidden Markov Models -- poster