MACHURA, Jakub, Helena GERŽOVÁ, Markéta MASOPUSTOVÁ and Marie VALÍČKOVÁ. Comparing majka and MorphoDiTa for Automatic Grammar Checking. In Horák, Aleš; Rychlý, Pavel; Rambousek, Adam (eds.). Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2019. Brno: Tribun EU, 2019, p. 3-14. ISBN 978-80-263-1530-8.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Comparing majka and MorphoDiTa for Automatic Grammar Checking
Name in Czech Porovnání majky a MorphoDiTy s ohledem na automatickou kontrolou gramatiky
Authors MACHURA, Jakub (203 Czech Republic, guarantor, belonging to the institution), Helena GERŽOVÁ (203 Czech Republic, belonging to the institution), Markéta MASOPUSTOVÁ (203 Czech Republic, belonging to the institution) and Marie VALÍČKOVÁ (203 Czech Republic, belonging to the institution).
Edition Brno, Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2019, p. 3-14, 12 pp. 2019.
Publisher Tribun EU
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 60203 Linguistics
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
Publication form printed version "print"
WWW URL
RIV identification code RIV/00216224:14210/19:00108375
Organization unit Faculty of Arts
ISBN 978-80-263-1530-8
ISSN 2336-4289
Keywords in English syntactic analysis; SET; grammar checker; punctuation; comma; homonymy; grammatical agreement; subject-predicate agreement; colloquial expressions; zeugma
Tags rivok
Tags International impact
Changed by Changed by: Mgr. et Mgr. Markéta Audy Masopustová, učo 415295. Changed: 26/5/2021 18:30.
Abstract
Developing a grammar checker requires the most accurate morphological analysis. We have been using the majka analyzer and DESAMB tagger so far, but due to certain obstacles to disambiguation, we encountered many errors in morphological analysis. Nowadays, there are several tools that achieve comparable results. Therefore, it was beneficial to test the one which is well-kept and open-source – the MorphoDiTa system. For the detection of grammatical, stylistic and punctuation errors we use mainly special grammars built into the SET parser and this paper presents results based on outputs of both morphological analyzers.
Links
TL02000146, research and development projectName: Webový pravopisný, gramatický a typografický korektor pro český jazyk
Investor: Technology Agency of the Czech Republic
PrintDisplayed: 28/4/2024 14:56