Automatic Grammar Correction of Commas in Czech Written Texts :
Comparative Study

D 2022

Automatic Grammar Correction of Commas in Czech Written Texts : Comparative Study

MACHURA, Jakub; Adam FRÉMUND a Jan ŠVEC

Základní údaje

Originální název

Automatic Grammar Correction of Commas in Czech Written Texts : Comparative Study

Autoři

MACHURA, Jakub (203 Česká republika, garant, domácí); Adam FRÉMUND (203 Česká republika) a Jan ŠVEC (203 Česká republika)

Vydání

Cham (CH), Text, Speech, and Dialogue : 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings, od s. 113-124, 12 s. 2022

Nakladatel

Springer

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

60203 Linguistics

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

Conference paper

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14210/22:00126700

Organizační jednotka

Filozofická fakulta

ISBN

978-3-031-16269-5

ISSN

DOI

https://doi.org/10.1007/978-3-031-16270-1_10

UT WoS

000866222300010

EID Scopus

2-s2.0-85139022640

Klíčová slova česky

Oprava gramatických chyb; lingvistická pravidla; neuronové sítě

Klíčová slova anglicky

Grammatical error correction; Linguistic rules; Transfer learning

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 3. 4. 2023 16:08, Mgr. et Mgr. Lucie Racyn

Anotace

V originále

The task of grammatical error correction is a widely studied field of natural language processing where the traditional rule-based approaches compete with the machine learning methods. The rule-based approach benefits mainly from a wide knowledge base available for a given language. On the contrary, the transfer learning methods and especially the use of pre-trained Transformers have the ability to be trained from a huge number of texts in a given language. In this paper, we focus on the task of automatic correction of missing commas in Czech written texts and we compare the rule-based approach with the Transformer-based model trained for this task.

Návaznosti

MUNI/A/1137/2021, interní kód MU

Název: Lexikon a gramatika češtiny II - 2022

Investor: Masarykova univerzita, Lexikon a gramatika češtiny II - 2022

Citovat

MACHURA, Jakub; Adam FRÉMUND a Jan ŠVEC. Automatic Grammar Correction of Commas in Czech Written Texts : Comparative Study. Online. In Sojka, Petr; Horák, Aleš; Kopeček, Ivan; Pala, Karel. Text, Speech, and Dialogue : 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings. Cham (CH): Springer, 2022, s. 113-124. ISBN 978-3-031-16269-5. Dostupné z: https://doi.org/10.1007/978-3-031-16270-1_10.

@inproceedings{2218767,
   author = {Machura, Jakub and Frémund, Adam and Švec, Jan},
   address = {Cham (CH)},
   booktitle = {Text, Speech, and Dialogue : 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings},
   doi = {https://doi.org/10.1007/978-3-031-16270-1_10},
   editor = {Sojka, Petr; Horák, Aleš; Kopeček, Ivan; Pala, Karel},
   keywords = {Grammatical error correction; Linguistic rules; Transfer learning},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Cham (CH)},
   isbn = {978-3-031-16269-5},
   pages = {113-124},
   publisher = {Springer},
   title = {Automatic Grammar Correction of Commas in Czech Written Texts : Comparative Study},
   url = {https://doi.org/10.1007/978-3-031-16270-1_10},
   year = {2022}
}

TY  - CONF
ID  - 2218767
AU  - Machura, Jakub - Frémund, Adam - Švec, Jan
PY  - 2022
TI  - Automatic Grammar Correction of Commas in Czech Written Texts : Comparative Study
PB  - Springer
CY  - Cham (CH)
SN  - 9783031162695
KW  - Grammatical error correction
KW  - Linguistic rules
KW  - Transfer learning
UR  - https://doi.org/10.1007/978-3-031-16270-1_10
N2  - The task of grammatical error correction is a widely studied field of natural language processing where the traditional rule-based approaches compete with the machine learning methods. The rule-based approach benefits mainly from a wide knowledge base available for a given language. On the contrary, the transfer learning methods and especially the use of pre-trained Transformers have the ability to be trained from a huge number of texts in a given language. In this paper, we focus on the task of automatic correction of missing commas in Czech written texts and we compare the rule-based approach with the Transformer-based model trained for this task.
ER  -

MACHURA, Jakub; Adam FRÉMUND a Jan ŠVEC. Automatic Grammar Correction of Commas in Czech Written Texts : Comparative Study. Online. In Sojka, Petr; Horák, Aleš; Kopeček, Ivan; Pala, Karel. \textit{Text, Speech, and Dialogue : 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings}. Cham (CH): Springer, 2022, s.~113-124. ISBN~978-3-031-16269-5. Dostupné z: https://doi.org/10.1007/978-3-031-16270-1\_{}10.

Přehled o publikaci