GermDetect: Verb Placement Error Detection Datasets for Learners of Germanic Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3A4WGXVVW8" target="_blank" >RIV/00216208:11320/26:4WGXVVW8 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.bea-1.59/" target="_blank" >https://aclanthology.org/2025.bea-1.59/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.bea-1.59" target="_blank" >10.18653/v1/2025.bea-1.59</a>

Jazyk výsledku

angličtina

Název v původním jazyce

GermDetect: Verb Placement Error Detection Datasets for Learners of Germanic Languages

Popis výsledku v původním jazyce

Correct verb placement is difficult to acquire for second-language (L2) learners of Germanic languages. However, word order errors and, consequently, verb placement errors, are heavily underrepresented in benchmark datasets of NLP tasks such as grammatical error detection (GED)/correction (GEC) and linguistic acceptability assessment (LA). If they are present, they are most often naively introduced, or classification occurs at the sentence level, preventing the precise identification of individual errors and the provision of appropriate feedback to learners. To remedy this, we present GermDetect: Universal Dependencies-based (UD), linguistically informed verb placement error detection datasets for learners of Germanic languages, designed as a token classification task. As our datasets are UD-based, we are able to provide them in most major Germanic languages: Afrikaans, German, Dutch, Faroese, Icelandic, Danish, Norwegian (Bokmål and Nynorsk), and Swedish. We train multilingual BERT (mBERT) models on GermDetect and show that linguistically informed, UD-based error induction results in more effective models for verb placement error detection than models trained on naively introduced errors. Finally, we conduct ablation studies on multilingual training and find that lower-resource languages benefit from the inclusion of structurally related languages in training.

Název v anglickém jazyce

GermDetect: Verb Placement Error Detection Datasets for Learners of Germanic Languages

Popis výsledku anglicky

Correct verb placement is difficult to acquire for second-language (L2) learners of Germanic languages. However, word order errors and, consequently, verb placement errors, are heavily underrepresented in benchmark datasets of NLP tasks such as grammatical error detection (GED)/correction (GEC) and linguistic acceptability assessment (LA). If they are present, they are most often naively introduced, or classification occurs at the sentence level, preventing the precise identification of individual errors and the provision of appropriate feedback to learners. To remedy this, we present GermDetect: Universal Dependencies-based (UD), linguistically informed verb placement error detection datasets for learners of Germanic languages, designed as a token classification task. As our datasets are UD-based, we are able to provide them in most major Germanic languages: Afrikaans, German, Dutch, Faroese, Icelandic, Danish, Norwegian (Bokmål and Nynorsk), and Swedish. We train multilingual BERT (mBERT) models on GermDetect and show that linguistically informed, UD-based error induction results in more effective models for verb placement error detection than models trained on naively introduced errors. Finally, we conduct ablation studies on multilingual training and find that lower-resource languages benefit from the inclusion of structurally related languages in training.

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

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications

ISBN

979-8-89176-270-1

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

818-829

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Vienna, Austria

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—