Tailored Fine-tuning for Comma Insertion in Czech
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3A3Q8YSIL2" target="_blank" >RIV/00216208:11320/26:3Q8YSIL2 - isvavai.cz</a>
Alternative codes found
RIV/00216208:90244/25:10513784
Result on the web
<a href="http://dx.doi.org/10.2478/jazcas-2025-0024" target="_blank" >http://dx.doi.org/10.2478/jazcas-2025-0024</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.2478/jazcas-2025-0024" target="_blank" >10.2478/jazcas-2025-0024</a>
Alternative languages
Result language
angličtina
Original language name
Tailored Fine-tuning for Comma Insertion in Czech
Original language description
Transfer learning techniques, particularly the use of pre-trained Transformers, can be trained on vast amounts of text in a particular language and can be tailored to specific grammar correction tasks, such as automatic punctuation correction. The Czech pre-trained RoBERTa model demonstrates outstanding performance in this task (Machura et al. 2022); however, previous attempts to improve the model have so far led to a slight degradation (Machura et al. 2023). In this paper, we present a more targeted fine-tuning of this model, addressing linguistic phenomena that the base model overlooked. Additionally, we provide a comparison with other models trained on a more diverse dataset beyond just web texts. © 2025 Jakub Machura et al., published by Slovak Academy of Sciences, Ľudovít Štúr Institute of Linguistics.
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Jazykovedny Casopis
ISSN
0021-5597
e-ISSN
—
Volume of the periodical
76
Issue of the periodical within the volume
1
Country of publishing house
US - UNITED STATES
Number of pages
11
Pages from-to
268-278
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-105025792668