Comparing majka and MorphoDiTa for Automatic Grammar Checking
| Authors | |
|---|---|
| Year of publication | 2019 |
| Type | Article in Proceedings |
| Conference | Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2019 |
| MU Faculty or unit | |
| Citation | |
| Web | https://nlp.fi.muni.cz/raslan/2019/paper03-machura.pdf |
| Keywords | syntactic analysis; SET; grammar checker; punctuation; comma; homonymy; grammatical agreement; subject-predicate agreement; colloquial expressions; zeugma |
| Description | 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. |
| Related projects: |