@inproceedings{chifligarov-etal-2025-automated,
title = "Automated Scoring of a {G}erman Written Elicited Imitation Test",
author = "Chifligarov, Mihail and
La{\^a}guidi, Jammila and
Schellenberg, Max and
Dill, Alexander and
Timukova, Anna and
Drackert, Anastasia and
Laarmann-Quante, Ronja",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.18/",
doi = "10.18653/v1/2025.bea-1.18",
pages = "237--247",
ISBN = "979-8-89176-270-1",
abstract = "We present an approach to the automated scoring of a German Written Elicited Imitation Test, designed to assess literacy-dependent procedural knowledge in German as a foreign language. In this test, sentences are briefly displayed on a screen and, after a short pause, test-takers are asked to reproduce the sentence in writing as accurately as possible. Responses are rated on a 5-point ordinal scale, with grammatical errors typically penalized more heavily than lexical deviations. We compare a rule-based model that implements the categories of the scoring rubric through hand-crafted rules, and a deep learning model trained on pairs of stimulus sentences and written responses. Both models achieve promising performance with quadratically weighted kappa (QWK) values around .87. However, their strengths differ {--} the rule-based model performs better on previously unseen stimulus sentences and at the extremes of the rating scale, while the deep learning model shows advantages in scoring mid-range responses, for which explicit rules are harder to define."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chifligarov-etal-2025-automated">
<titleInfo>
<title>Automated Scoring of a German Written Elicited Imitation Test</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Chifligarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jammila</namePart>
<namePart type="family">Laâguidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Schellenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Dill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Timukova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Drackert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>We present an approach to the automated scoring of a German Written Elicited Imitation Test, designed to assess literacy-dependent procedural knowledge in German as a foreign language. In this test, sentences are briefly displayed on a screen and, after a short pause, test-takers are asked to reproduce the sentence in writing as accurately as possible. Responses are rated on a 5-point ordinal scale, with grammatical errors typically penalized more heavily than lexical deviations. We compare a rule-based model that implements the categories of the scoring rubric through hand-crafted rules, and a deep learning model trained on pairs of stimulus sentences and written responses. Both models achieve promising performance with quadratically weighted kappa (QWK) values around .87. However, their strengths differ – the rule-based model performs better on previously unseen stimulus sentences and at the extremes of the rating scale, while the deep learning model shows advantages in scoring mid-range responses, for which explicit rules are harder to define.</abstract>
<identifier type="citekey">chifligarov-etal-2025-automated</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.18</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.18/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>237</start>
<end>247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Scoring of a German Written Elicited Imitation Test
%A Chifligarov, Mihail
%A Laâguidi, Jammila
%A Schellenberg, Max
%A Dill, Alexander
%A Timukova, Anna
%A Drackert, Anastasia
%A Laarmann-Quante, Ronja
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F chifligarov-etal-2025-automated
%X We present an approach to the automated scoring of a German Written Elicited Imitation Test, designed to assess literacy-dependent procedural knowledge in German as a foreign language. In this test, sentences are briefly displayed on a screen and, after a short pause, test-takers are asked to reproduce the sentence in writing as accurately as possible. Responses are rated on a 5-point ordinal scale, with grammatical errors typically penalized more heavily than lexical deviations. We compare a rule-based model that implements the categories of the scoring rubric through hand-crafted rules, and a deep learning model trained on pairs of stimulus sentences and written responses. Both models achieve promising performance with quadratically weighted kappa (QWK) values around .87. However, their strengths differ – the rule-based model performs better on previously unseen stimulus sentences and at the extremes of the rating scale, while the deep learning model shows advantages in scoring mid-range responses, for which explicit rules are harder to define.
%R 10.18653/v1/2025.bea-1.18
%U https://aclanthology.org/2025.bea-1.18/
%U https://doi.org/10.18653/v1/2025.bea-1.18
%P 237-247
Markdown (Informal)
[Automated Scoring of a German Written Elicited Imitation Test](https://aclanthology.org/2025.bea-1.18/) (Chifligarov et al., BEA 2025)
ACL
- Mihail Chifligarov, Jammila Laâguidi, Max Schellenberg, Alexander Dill, Anna Timukova, Anastasia Drackert, and Ronja Laarmann-Quante. 2025. Automated Scoring of a German Written Elicited Imitation Test. In Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025), pages 237–247, Vienna, Austria. Association for Computational Linguistics.