Constructing a Lexical Resource of Russian Derivational Morphology

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 2788–2797 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 2788 Constructing a Lexical Resource of Russian Derivational Morphology Lukáš Kyjánek⋄, Olga Lyashevskaya•, Anna Nedoluzhko⋄, Daniil Vodolazsky , Zdeněk Žabokrtský⋄ ⋄Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic •National Research University Higher School of Economics, Moscow, Russia Sber, Moscow, Russia {kyjanek, nedoluzko, zabokrtsky}@ufal.mff.cuni.cz olesar@yandex.ru daniil.vodolazsky@mail.ru Abstract Words of any language are to some extent related thought the ways they are formed. For instance, the verb exempl-ify and the noun example-s are both based on the word example, but the verb is derived from it, while the noun is inflected. In Natural Language Processing of Russian, the inflection is satisfactorily processed; however, there are only a few machine-trackable resources that capture derivations even though Russian has both of these morphological processes very rich. Therefore, we devote this paper to improving one of the methods of constructing such resources and to the application of the method to a Russian lexicon, which results in the creation of the largest lexical resource of Russian derivational relations. The resulting database dubbed DeriNet.RU includes more than 300 thousand lexemes connected with more than 164 thousand binary derivational relations. To create such data, we combined the existing machine-learning methods that we improved to manage this goal. The whole approach is evaluated on our newly created data set of manual, parallel annotation. The resulting DeriNet.RU is freely available under an open license agreement. Keywords: Russian, language resource, derivational network, derivational morphology, machine learning 1. Introduction Russian is a language with rich derivational morphol- ogy (Štekauer et al., 2012; Körtvélyessy, 2016) and yet there are only a few resources and tools to process it compared to those for inflectional morphology.1 In- deed, in Natural Language Processing, the two morpho- logical processes are usually kept apart. They are dis- tinguished on the basis of their regularity and meaning of affixes that are attached to so-called morphological bases when coining inflected or derived words. First, the inflectional morphology seems to be more regular than derivational morphology. Second, an attached af- fix in the process of inflection/derivation conveys dif- ferent meaning (grammatical/lexical), see Lipka (2010, p. 71). From this perspective, inflection is the main source of word forms because it conveys grammatical categories, such as cases and tenses, by attaching gram- matical affixes, while derivation is the main source of new lexemes as it changes the lexical meaning by at- taching lexical affixes. For instance, the noun учителя ‘uchitelya’ (teachers) is inflected by attaching the in- flectional affix -я ‘-ya’ to the morphological base of the noun учитель ‘uchitel’ (teacher), which is derived by attaching the lexical affix -тель ‘-tel’ to the morpholog- ical base of the verb учить ‘uchit’ (to teach).2 1Reynolds (2016, pp.12-55) provides an overview of re- sources and tools for processing Russian inflection. 2It should be mentioned here that a boundary between the two morphological processes is fuzzy. Linguists …

Content truncated to 500 words