Abstract
The information about verb’s aspect and its aspectual pair should be available to algorithms for languages where this feature is present. This paper presents an algorithm that automatically detects morphological dependencies between verbs in Polish and uses them to match corresponding perfective and imperfective verbs. The results of the algorithm are tested against Słownik Gramatyczny Języka Polskiego.
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.
From here on this article refers to Polish, unless stated otherwise.
- 2.
They can be used in future tense using a grammar construct consisting of verb to be and infinitive or past tense form.
- 3.
see Sect. 3.
- 4.
As they actually do in English and other languages where the aspect is associated with a grammatical construction rather than a verb itself.
- 5.
Namely: if attaching the prefix would create difficult to pronounce conglomerate of consonants.
- 6.
Please note, that zmyć has already been created from myć with a prefix.
- 7.
The algorithm works only on orthographic forms and so all examples in this paper are also in the orthographic forms.
- 8.
Ź is a palatal z. In ortographic form of zamrozić there is z but it becomes palatal due to the following i.
- 9.
Order of suffixes with the same length is irrelevant, since two different suffixes cannot match at the same time.
- 10.
with e added or removed.
- 11.
CLP does not include so called potential verbs, i.e. verbs which can be created by regular morphological processes, e.g. from a noun, by replacing the inflection ending with suffix -ować. For example the verb bistrować may be created in this way from the noun bistro. Bistrować is not registered in dictionary of Polish but many potential verbs enter to dictionaries each year.
References
Gajęcki, M.: Słownik fleksyjny jako biblioteka języka C. In: Lubaszewski, W. (ed.) Słowniki komputerowe i automatyczna ekstrakcja informacji z tekstu pod red. W. Lubaszewskiego, chap. 6, pp. 107–134. Uczelniane Wydawnictwa Naukowo-Dydaktyczne AGH, Kraków (2009)
Gołąb, Z., Heinz, A., Polański, K.: Słownik Terminologii Językoznawczej. Państwowe Wydawnictwo Naukowe, Warszawa (1968)
Lubaszewski, W.: Program automatycznej segmentacji morfologicznej (na materiale polskich czasowników). POLONICA II 21–32, (1976)
Lubaszewski, W., Wróbel, H., Gajęcki, M., Moskal, B., Orzechowska, A., Pietras, P., Pisarek, P., Rokicka, T.: Słownik fleksyjny języka polskiego. Wydawnictwo Prawnicze LexisNexis, Kraków (2001)
Perlin, J.: Ile jest we współczesnej polszczyónie czasownikźw dwuaspektowych? Linguistica Copernicana 1(3), 165–171 (2010)
Pisarek, P.: Słownik fleksyjny. In: Lubaszewski, W. (ed.) Słowniki komputerowe i automatyczna ekstrakcja informacji z tekstu pod red. W. Lubaszewskiego, chap. 6, pp. 37–67. Uczelniane Wydawnictwa Naukowo-Dydaktyczne AGH, Kraków (2009)
Saloni, Z.: Podstawy teoretyczne “Słownika gramatycznego języka polskiego”, Warszawa (2012)
Acknowledgment
This research was partially funded by AGH University of Science and Technology Statutory Fund.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kaleta, Z. (2020). Automatic Pairing of Perfective and Imperfective Verbs in Polish. In: Vetulani, Z., Paroubek, P., Kubis, M. (eds) Human Language Technology. Challenges for Computer Science and Linguistics. LTC 2017. Lecture Notes in Computer Science(), vol 12598. Springer, Cham. https://doi.org/10.1007/978-3-030-66527-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-66527-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66526-5
Online ISBN: 978-3-030-66527-2
eBook Packages: Computer ScienceComputer Science (R0)