Abstract
In this paper we discuss the intricacies of Polish language part of speech tagging, present the current state of the art by comparing available taggers in detail and show the main obstacles that are a limiting factor in achieving an accuracy of Polish POS tagging higher than 91% of correctly tagged word segments. As this result is not only lower than in the case of English taggers, but also below those for other highly inflective languages, such as Czech and Slovene, we try to identify the main weaknesses of the taggers, their underlying algorithms, the training data, or difficulties inherent to the language to explain this difference. For this purpose we analyze the errors made individually by each of the available Polish POS taggers, an ensemble of the taggers and also by a publicly available well-known OpenNLP tagger, adapted to Polish tagset. Finally, we propose further steps that should be taken to narrow down the gap between Polish and English POS tagging performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
IPI PAN corpus was the first large, POS-tagged reference corpus of Polish, now superseded by the National Corpus of Polish.
- 2.
Now available also on-line at http://sgjp.pl.
- 3.
- 4.
As the difference in accuracy between these two approaches turned out not to be statistically significant, we have limited further experiments to maximum entropy models. Trained models available at: http://zil.ipipan.waw.pl/OpenNLP.
- 5.
In fact, this number is further reduced by the morphosyntactic analyser.
- 6.
One exception from this general observation are gerunds (ger), which are however systematically homonymous with nouns and thus are extremely difficult to disambiguate not only for taggers, but also for the human annotator.
- 7.
This phenomenon is typical of fusional languages such as Polish and other Slavonic languages.
References
Manning, C.D.: Part-of-speech tagging from 97% to 100%: is it time for some linguistics? In: Gelbukh, A.F. (ed.) CICLing 2011. LNCS, vol. 6608, pp. 171–189. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19400-9_14
Przepiórkowski, A., Woliński, M.: The unbearable lightness of tagging: a case study in morphosyntactic tagging of polish. In: Proceedings of the 4th International Workshop on Linguistically Interpreted Corpora (LINC-03), EACL 2003, pp. 109–116 (2003)
Przepiórkowski, A.: A comparison of two morphosyntactic tagsets of Polish. In: Koseska-Toszewa, V., Dimitrova, L., Roszko, R. (eds.) Representing Semantics in Digital Lexicography: Proceedings of MONDILEX Fourth Open Workshop, Warsaw, pp. 138–144 (2009)
Woliński, M.: Morfeusz reloaded. [18], pp. 1106–1111
Woliński, M.: Morfeusz—a practical tool for the morphological analysis of polish. In: Kłopotek, M.A., Wierzchoń, S.T., Trojanowski, K. (eds.) Intelligent Information Processing and Web Mining. AINSC, vol. 35, pp. 503–512. Springer, Heidelberg (2006). https://doi.org/10.1007/3-540-33521-8_55
Saloni, Z., Woliński, M., Wołosz, R., Gruszczyński, W., Skowrońska, D.: Słownik gramatyczny jȩzyka polskiego, 2. edn. Warszawa (2012)
Przepiórkowski, A., Bańko, M., Górski, R., Lewandowska-Tomaszczyk, B. (eds.) Narodowy Korpus Jȩzyka Polskiego. Warszawa (2012)
Dȩbowski, Ł.: Trigram morphosyntactic tagger for polish. In: Kłopotek, M.A., Wierzchoń, S.T., Trojanowski, K. (eds.) Intelligent Information Processing and Web Mining. AINSC, vol. 25, pp. 409–413. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-39985-8_43
Piasecki, M.: Polish tagger TaKIPI: rule based construction and optimisation. Task Q. 11, 151–167 (2007)
Acedański, S.: A morphosyntactic brill tagger for inflectional languages. In: Loftsson, H., Rögnvaldsson, E., Helgadóttir, S. (eds.) NLP 2010. LNCS (LNAI), vol. 6233, pp. 3–14. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-14770-8_3
Radziszewski, A., Śniatowski, T.: A memory-based tagger for polish. In: Proceedings of the LTC 2011 (2011)
Radziszewski, A.: A tiered CRF tagger for Polish. In: Bembenik, R., Skonieczny, Ł., Rybiński, H., Kryszkiewicz, M., Niezgódka, M. (eds.) Intelligent Tools for Building a Scientific Information Platform: Advanced Architectures and Solutions. SCI, vol. 467, pp. 215–230. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-35647-6_16
Waszczuk, J.: Harnessing the CRF complexity with domain-specific constraints. The case of morphosyntactic tagging of a highly inflected language. In: Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012), Mumbai, India, pp. 2789–2804 (2012)
Kobyliński, Ł.: PoliTa: a multitagger for polish. [18], pp. 2949–2954
Radziszewski, A., Acedański, S.: Taggers gonna tag: an argument against evaluating disambiguation capacities of morphosyntactic taggers. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2012. LNCS (LNAI), vol. 7499, pp. 81–87. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32790-2_9
Awramiuk, E.: Systemowość polskiej homonimii międzyparadygmatycznej. Białystok (1999)
Radziszewski, A.: Evaluation of lemmatisation accuracy of four polish taggers. In: Proceedings of the LTC 2013 (2013)
Calzolari, N., Choukri, K., Declerck, T., Loftsson, H., Maegaard, B., Mariani, J., Moreno, A., Odijk, J., Piperidis, S., eds.: Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014, Reykjavík, Iceland, ELRA (2014)
Acknowledgment
Work partly financed by the Polish Ministry of Science and Higher Education, a program in support of scientific units involved in the development of a European research infrastructure for the humanities and social sciences in the scope of the CLARIN ERIC consortium and partly financed by Polish National Science Center grant 2014/15/B/HS2/03119.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Kobyliński, Ł., Kieraś, W. (2018). Part of Speech Tagging for Polish: State of the Art and Future Perspectives. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2016. Lecture Notes in Computer Science(), vol 9623. Springer, Cham. https://doi.org/10.1007/978-3-319-75477-2_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-75477-2_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75476-5
Online ISBN: 978-3-319-75477-2
eBook Packages: Computer ScienceComputer Science (R0)