Refining Czech GEC: Insights from a Multi-experiment Approach

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511642" target="_blank" >RIV/00216208:11320/25:10511642 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-032-02551-7_7" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-032-02551-7_7</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-032-02551-7_7" target="_blank" >10.1007/978-3-032-02551-7_7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Refining Czech GEC: Insights from a Multi-experiment Approach

Popis výsledku v původním jazyce

We present a grammar error correction (GEC) system that achieves state of the art for the Czech language. Our system is based on a neural network translation approach with the Transformer architecture, and its key feature is its real-time synthetic generation pipeline, which dynamically augments sentences with artificial errors by introducing both language-agnostic and Czech-specific errors. We conduct a comprehensive series of experiments, investigating the Czech GEC corpora as bases for synthetic error introduction, several error generation strategies, domain balancing, tokenization granularity, model size, and data scaling during fine-tuning. Additionally, we evaluate the performance of large language models (LLMs) on Czech GEC in both end-user and expert fine-tuning scenarios. Our best-performing model is superior both in performance and computational efficiency. The source code and the trained model links are available on https://github.com/ufal/tsd2025-gec.

Název v anglickém jazyce

Refining Czech GEC: Insights from a Multi-experiment Approach

Popis výsledku anglicky

We present a grammar error correction (GEC) system that achieves state of the art for the Czech language. Our system is based on a neural network translation approach with the Transformer architecture, and its key feature is its real-time synthetic generation pipeline, which dynamically augments sentences with artificial errors by introducing both language-agnostic and Czech-specific errors. We conduct a comprehensive series of experiments, investigating the Czech GEC corpora as bases for synthetic error introduction, several error generation strategies, domain balancing, tokenization granularity, model size, and data scaling during fine-tuning. Additionally, we evaluate the performance of large language models (LLMs) on Czech GEC in both end-user and expert fine-tuning scenarios. Our best-performing model is superior both in performance and computational efficiency. The source code and the trained model links are available on https://github.com/ufal/tsd2025-gec.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH23_020%2F0008518" target="_blank" >EH23_020/0008518: Jazykověda, umělá inteligence a jazykové a řečové technologie: od výzkumu k aplikacím</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

28th International Conference on Text, Speech and Dialogue (Part II)

ISBN

978-3-032-02551-7

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

64-76

Název nakladatele

Springer

Místo vydání

Cham, Switzerland

Místo konání akce

Erlangen, Germany

Datum konání akce

25. 8. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001576349100006