Crosslingual Content Scoring in Five Languages Using Machine-Translation and Multilingual Transformer Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AHPF75PD8" target="_blank" >RIV/00216208:11320/23:HPF75PD8 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/10.1007/s40593-023-00370-1" target="_blank" >https://link.springer.com/10.1007/s40593-023-00370-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s40593-023-00370-1" target="_blank" >10.1007/s40593-023-00370-1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Crosslingual Content Scoring in Five Languages Using Machine-Translation and Multilingual Transformer Models

Popis výsledku v původním jazyce

"Abstractn This paper investigates crosslingual content scoring, a scenario where scoring models trained on learner data in one language are applied to data in a different language. We analyze data in five different languages (Chinese, English, French, German and Spanish) collected for three prompts of the established English ASAP content scoring dataset. We cross the language barrier by means of both shallow and deep learning crosslingual classification models using both machine translation and multilingual transformer models. We find that a combination of machine translation and multilingual models outperforms each method individually - our best results are reached when combining the available data in different languages, i.e. first training a model on the large English ASAP dataset before fine-tuning on smaller amounts of training data in the target language."

Název v anglickém jazyce

Crosslingual Content Scoring in Five Languages Using Machine-Translation and Multilingual Transformer Models

Popis výsledku anglicky

"Abstractn This paper investigates crosslingual content scoring, a scenario where scoring models trained on learner data in one language are applied to data in a different language. We analyze data in five different languages (Chinese, English, French, German and Spanish) collected for three prompts of the established English ASAP content scoring dataset. We cross the language barrier by means of both shallow and deep learning crosslingual classification models using both machine translation and multilingual transformer models. We find that a combination of machine translation and multilingual models outperforms each method individually - our best results are reached when combining the available data in different languages, i.e. first training a model on the large English ASAP dataset before fine-tuning on smaller amounts of training data in the target language."

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

"International Journal of Artificial Intelligence in Education"

ISSN

1560-4292

e-ISSN

—

Svazek periodika

""

Číslo periodika v rámci svazku

2023-6-19

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

27

Strana od-do

1-27

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—