Using transitivity information for morphological and syntactic disambiguation of pronouns in Ukrainian

2019;
: pp. 101-115
1
1- Samsung Research Poland; 2 - Institute for Ukrainian, NGO
2
Institute for Ukrainian, NGO

The paper presents a short introduction to several electronic resources for Ukrainian
language, namely, two treebanks: the Gold standard (ab. 130 thousand tokens), manually
annotated in the Universal Dependencies flavour (https://universaldependencies.org/), which
comprises the training data for a machine-trained syntactic parser, and a big (near 3 billion
tokens), automatically annotated General Treebank (also known as Zvidusil), as well as a
valency dictionary, developed by the Institute for Ukrainian, NGO (Kyiv) in 2015-2019
(https://mova.institute/). We also describe an experimental usage of the valency dictionary
information to boost the performance of the syntactic parser. As a proof of concept, we discuss
the case of syntactic and morphological ambiguity of frequently used Ukrainian pronouns
його, її, їх ‘his, her, their’ and ways of improving the syntactic parser’s performance using the
supervised machine learning techniques with a theoretical linguistic support. Apart from the
multiple morphological ambiguity (24+ possible tags for each of these forms), one of the
challenges connected with the presented linguistic phenomenon, is that its correct
disambiguation involves anaphora resolution and semantic roles identification. On the one
hand, this makes the disambiguation process much more complicated, given the followed
annotation design, on the other hand, by resolving a seemingly low-level (morphological)
problem we gain a bonus in the form of significant textual analysis hints which can be later
used in various NLP applications for Ukrainian. The present article is a practical follow-up of
its more theoretical predecessor (Kotsyba, Moskalevskyi 2018 [11]), where the linguistic
underpinnings of the syntactic and morphological interpretation of the pronouns його, її, їх in
comparison with other Slavic languages are presented in greater detail.

1. Blodgett, A., Schneider, N. (2018). Semantic Supersenses for English Possessives. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki (Japan).

2. Danielewiczowa M. (2017). Polskie nazwy czynności i wytworów czynności w świetle walencji motywujących je czasowników /Polish Action Nominals in the Light of the Valency of the Corresponding Verbs. Prace Filologiczne, tom LXX, p. 143–157.

3. de Marneffe M.-C., Dozat T., Silveira N., Haverinen K., Ginter F., Nivre J., and Manning Ch.- D. (2014). Universal Stanford Dependencies: A cross-linguistic typology. LREC.

4. Dozat, T., Qi, P., Manning Ch.-D. (2017). Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task. Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Vancouver, Canada, August 3–4, 2017, p. 20–30.

5. Erjavec T. (2009). MULTEXT-East Morphosyntactic Specifications: Towards Version 4. Proc. of the MONDILEX Third Open Workshop, Bratislava, Slovakia, 15–16 April, 2009.

6. Kocková, J. (2017). Substantiva mezi slovesem a jménem Substantiva na -ní (-tí) / -ние (-тие) v češtině a ruštině ve světle paralelního korpusu. Časopis pro Moderní Filologii 99, Č. 1, p. 55–64.

7. Kotsyba N. (2013). Overview of the Ukrainian language resources within the multilingual European MULTEXT-East project, v. 4. Вісник Національного університету "Львівська політехніка". № 770: Інформаційні системи та мережі. p. 122–129. http://science.lp.edu.ua/sisn/vol-770-no-2013-1

8. Kotsyba, N. (2014). How light are aspectual meanings?: A study of the relation between light verbs and lexical aspects in Ukrainian. Robering, K. (ed.) Events, Arguments, and Aspects. Topics in the Semantics of Verbs. Studies in Language Companion Series, vol. 152, pp. 261–300.

9. Kotsyba N. (2014). Using Polish Wordnet for Predicting Semantic Roles for the Valency Dictionary of Polish Verbs. Przepiórkowski A., Ogrodniczuk M. (eds) Advances in Natural Language Processing. NLP 2014. Lecture Notes in Computer Science, vol 8686. Springer International Publishing Switzerland, p. 202–207. https://link.springer.com/chapter/10.1007/978-3-319-10888-9_21

10. Kotsyba, N., Moskalevskyi, B. (2018). An essential infrastructure of Ukrainian language resources and its possible applications. SlaviCorp 2018, 24–26 September 2018, Charles University, Prague, Book of Abstracts. https://slavicorp.ff.cuni.cz/wp-content/uploads/sites/144/2018/09/ SlaviCorp2018_Book_of_Abstracts.pdf

11. Kotsyba, N., Moskalevskyi, B. (2018). Syntactic and morphological ambiguity of the deverbal nouns’ arguments in Ukrainian and ways of its resolution. Prace Filologiczne, vol. VXXII, Warsaw, p. 193–210.

12. Levin, B. and Rappaport Hovav M. (2005). Argument realization. Cambridge: Cambridge University Press.

13. Panevová, J. (2017). Od valence slovesa k valenci substantiv a adjektiv/From Valency of Verbs to Valency of Nouns and Adjectives. Prace Filologiczne, vol. LXX, Warsaw, p. 59–72.

14. Pazelskaya, A. (2007). Argument structure in Russian deverbal nouns in -nie. Studies in Formal Slavic Linguistics, ed. Franc Maršič and Rok Zeucer, p. 255–272. Peter Lang.

15. Petrov S., Das D., and McDonald R. (2012). A universal part-of-speech tagset. LREC.

16. Pustejovsky, J. (1995). The Generative Lexicon, MIT Press, Cambridge, MA.

17. Straka M., Hajič J., Straková J. (2016). UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portorož, Slovenia, May 2016.

18. Zeman, D. (2008). Reusable Tagset Conversion Using Tagset Drivers. LREC.

19. Vykhovanets I., Horodenska K. Theoretical Morphology of Ukrainian Language: Academic Grammar of Ukr. Lang. Kyiv: Pulsary, 2004. [Ukrainian]

20. Kobozeva I.M. About Possessivity in Russian: Possessive Predicates and the Genitive. Acta Linguistica Petropolitana. Scientific Papers of Institute for Linguistic Research RAS. T. XI. P. 1. Categories of Noun and Verb in the System of Functional Grammar. Nauka, S. Petersburg, p. 249–271, 2015. [Russian]

21. Kurylo, O. Considerations about the Modern Ukrainian Literary Language. Solomiya Pavlychko’s Publishing House “Osnovy”, Kyiv, 2004 (reprint from Knyhospilka, 1925). [Ukrainian]

22. Pazelskaya A. G., Tatevosov S. G., The Deverbal Noun and the Structure of the Russian Verb. V. A. Plungian, S. G. Tatevosov (ed.), Research on Verbal Derivation. Languages of the Slavic Culture. Moscow, p. 348–380, 2008. [Russian]

23. Pchelintseva, J. E. The Grammatical Status and Aspectuality of Deverbal Nouns of Action in Ukrainian (on the background of Russian and Polish). Izvestiya VGPU. Philological Studies. Volgograd, 2015. [Russian]

24. Syniavskyi O. N. The Norms of the Ukrainian Literary Language. Ukrainian Publisher, 2nd edition, Lviv, 1941. [Ukrainian]

25. Syntactic corpus search interface. Retrieved March 19, 2019, from http://www.mova.info/syntaxis_search.aspx. [Ukrainian]

26. SUM – Dictionary of Ukrainian language in 11 volumes. „Naukova Dumka”, Kyiv, 1970–1980. Digital version of SUM. Retrieved March 19, 2019, from http://sum.in.ua/. [Ukrainian]

27. IU Gold – Syntactic Corpus of the Ukrainian Language (Gold Standard Treebank of Ukrainian). Institute for Ukrainian, NGO, 2018. Retrieved March 19, 2019, from https://mova.institute [Ukrainian]