A machine learning approach to Czech readability

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A90244%2F24%3A10495705" target="_blank" >RIV/00216208:90244/24:10495705 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.4995/EuroCALL2023.2023.16991" target="_blank" >https://doi.org/10.4995/EuroCALL2023.2023.16991</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.4995/EuroCALL2023.2023.16991" target="_blank" >10.4995/EuroCALL2023.2023.16991</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A machine learning approach to Czech readability

Popis výsledku v původním jazyce

We present a new corpus of Czech texts labeled for second-language readability, and show results of experiments to train machine-learning classifiers to automatically label new texts according to reading level. We report results comparing the performance of traditional machine-learning models (including Random Forest, XGBoost, Linear Discriminant Analysis, and XGBoost Random Forest) and a neural network (XLM-RoBERTa). The results of our research can be implemented in tools to support learning Czech, a less commonly taught language. We extract 46 linguistic features in various categories for use with traditional machine-learning algorithms. We train models on these features and evaluate their performance with recursive feature elimination to determine how informative each feature is for each model. We then compare those results to those of a transformer trained for the same task on the same corpus. XGBoost achieves the highest accuracy at 0.81, suggesting that these traditional models can still perform as well as, or better, than newer models on this task. Notably, the transformer has the lowest mean F1 at 0.74.

Název v anglickém jazyce

A machine learning approach to Czech readability

Popis výsledku anglicky

We present a new corpus of Czech texts labeled for second-language readability, and show results of experiments to train machine-learning classifiers to automatically label new texts according to reading level. We report results comparing the performance of traditional machine-learning models (including Random Forest, XGBoost, Linear Discriminant Analysis, and XGBoost Random Forest) and a neural network (XLM-RoBERTa). The results of our research can be implemented in tools to support learning Czech, a less commonly taught language. We extract 46 linguistic features in various categories for use with traditional machine-learning algorithms. We train models on these features and evaluate their performance with recursive feature elimination to determine how informative each feature is for each model. We then compare those results to those of a transformer trained for the same task on the same corpus. XGBoost achieves the highest accuracy at 0.81, suggesting that these traditional models can still perform as well as, or better, than newer models on this task. Notably, the transformer has the lowest mean F1 at 0.74.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

EuroCALL 2023. CALL for all Languages

ISBN

978-84-13-96131-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

159-164

Název nakladatele

Universitat Politècnica de València

Místo vydání

Valencie

Místo konání akce

University of Iceland

Datum konání akce

15. 8. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—