Magda Ševčíková


The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
Khuyagbaatar Batsuren | Gábor Bella | Aryaman Arora | Viktor Martinovic | Kyle Gorman | Zdeněk Žabokrtský | Amarsanaa Ganbold | Šárka Dohnalová | Magda Ševčíková | Kateřina Pelegrinová | Fausto Giunchiglia | Ryan Cotterell | Ekaterina Vylomova
Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29% F1 score across all languages, ranging English (93.84%) to Latin (99.38%). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentences in 3 languages (Czech, English, Mongolian), received 10 system submissions from 3 teams, and the best systems outperformed all three state-of-the-art subword tokenization methods (BPE, ULM, Morfessor2) by 30.71% absolute. To facilitate error analysis and support any type of future studies, we released all system predictions, the evaluation script, and all gold standard datasets.

Towards Universal Segmentations: UniSegments 1.0
Zdeněk Žabokrtský | Niyati Bafna | Jan Bodnár | Lukáš Kyjánek | Emil Svoboda | Magda Ševčíková | Jonáš Vidra
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Our work aims at developing a multilingual data resource for morphological segmentation. We present a survey of 17 existing data resources relevant for segmentation in 32 languages, and analyze diversity of how individual linguistic phenomena are captured across them. Inspired by the success of Universal Dependencies, we propose a harmonized scheme for segmentation representation, and convert the data from the studied resources into this common scheme. Harmonized versions of resources available under free licenses are published as a collection called UniSegments 1.0.


pdf bib
Sentence Meaning Representations Across Languages: What Can We Learn from Existing Frameworks?
Zdeněk Žabokrtský | Daniel Zeman | Magda Ševčíková
Computational Linguistics, Volume 46, Issue 3 - September 2020

This article gives an overview of how sentence meaning is represented in eleven deep-syntactic frameworks, ranging from those based on linguistic theories elaborated for decades to rather lightweight NLP-motivated approaches. We outline the most important characteristics of each framework and then discuss how particular language phenomena are treated across those frameworks, while trying to shed light on commonalities as well as differences.


pdf bib
Proceedings of the Second International Workshop on Resources and Tools for Derivational Morphology
Magda Ševčíková | Zdeněk Žabokrtský | Eleonora Litta | Marco Passarotti
Proceedings of the Second International Workshop on Resources and Tools for Derivational Morphology

DeriNet 2.0: Towards an All-in-One Word-Formation Resource
Jonáš Vidra | Zdeněk Žabokrtský | Magda Ševčíková | Lukáš Kyjánek
Proceedings of the Second International Workshop on Resources and Tools for Derivational Morphology

Universal Derivations Kickoff: A Collection of Harmonized Derivational Resources for Eleven Languages
Lukáš Kyjánek | Zdeněk Žabokrtský | Magda Ševčíková | Jonáš Vidra
Proceedings of the Second International Workshop on Resources and Tools for Derivational Morphology


Semi-Automatic Construction of Word-Formation Networks (for Polish and Spanish)
Mateusz Lango | Magda Ševčíková | Zdeněk Žabokrtský
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)


Merging Data Resources for Inflectional and Derivational Morphology in Czech
Zdeněk Žabokrtský | Magda Ševčíková | Milan Straka | Jonáš Vidra | Adéla Limburská
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

The paper deals with merging two complementary resources of morphological data previously existing for Czech, namely the inflectional dictionary MorfFlex CZ and the recently developed lexical network DeriNet. The MorfFlex CZ dictionary has been used by a morphological analyzer capable of analyzing/generating several million Czech word forms according to the rules of Czech inflection. The DeriNet network contains several hundred thousand Czech lemmas interconnected with links corresponding to derivational relations (relations between base words and words derived from them). After summarizing basic characteristics of both resources, the process of merging is described, focusing on both rather technical aspects (growth of the data, measuring the quality of newly added derivational relations) and linguistic issues (treating lexical homonymy and vowel/consonant alternations). The resulting resource contains 970 thousand lemmas connected with 715 thousand derivational relations and is publicly available on the web under the CC-BY-NC-SA license. The data were incorporated in the MorphoDiTa library version 2.0 (which provides morphological analysis, generation, tagging and lemmatization for Czech) and can be browsed and searched by two web tools (DeriNet Viewer and DeriNet Search tool).


Word-Formation Network for Czech
Magda Ševčíková | Zdeněk Žabokrtský
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

In the present paper, we describe the development of the lexical network DeriNet, which captures core word-formation relations on the set of around 266 thousand Czech lexemes. The network is currently limited to derivational relations because derivation is the most frequent and most productive word-formation process in Czech. This limitation is reflected in the architecture of the network: each lexeme is allowed to be linked up with just a single base word; composition as well as combined processes (composition with derivation) are thus not included. After a brief summarization of theoretical descriptions of Czech derivation and the state of the art of NLP approaches to Czech derivation, we discuss the linguistic background of the network and introduce the formal structure of the network and the semi-automatic annotation procedure. The network was initialized with a set of lexemes whose existence was supported by corpus evidence. Derivational links were created using three sources of information: links delivered by a tool for morphological analysis, links based on an automatically discovered set of derivation rules, and on a grammar-based set of rules. Finally, we propose some research topics which could profit from the existence of such lexical network.


Prague Dependency Treebank 2.5 – a Revisited Version of PDT 2.0
Eduard Bejček | Jarmila Panevová | Jan Popelka | Pavel Straňák | Magda Ševčíková | Jan Štěpánek | Zdeněk Žabokrtský
Proceedings of COLING 2012


Annotation of Morphological Meanings of Verbs Revisited
Jarmila Panevová | Magda Ševčíková
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

Meanings of morphological categories are an indispensable component of representation of sentence semantics. In the Prague Dependency Treebank 2.0, sentence semantics is represented as a dependency tree consisting of labeled nodes and edges. Meanings of morphological categories are captured as attributes of tree nodes; these attributes are called grammatemes. The present paper focuses on morphological meanings of verbs, i.e. on meanings of the morphological category of tense, mood, aspect etc. After several introductory remarks, seven verbal grammatemes used in the PDT 2.0 annotation scenario are briefly introduced. After that, each of the grammatemes is examined. Three verbal grammatemes of the original set were included in the new set without changes, one of the grammatemes was extended, and three of them were substituted for three new ones. The revised grammateme set is to be included in the forthcoming version of PDT (tentatively called PDT 3.0). Rules for automatic and manual assignment of the revised grammatemes are further discussed in the paper.