@inproceedings{laarmann-quante-etal-2024-automatic-extraction,
title = "Automatic Extraction of Nominal Phrases from {G}erman Learner Texts of Different Proficiency Levels",
author = {Laarmann-Quante, Ronja and
M{\"u}ller, Marco and
Belke, Eva},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.172",
pages = "1925--1931",
abstract = "Correctly inflecting determiners and adjectives so that they agree with the noun in nominal phrases (NPs) is a big challenge for learners of German. Given the increasing number of available learner corpora, a large-scale corpus-based study on the acquisition of this aspect of German morphosyntax would be desirable. In this paper, we present a pilot study in which we investigate how well nouns, their grammatical heads and the dependents that have to agree with the noun can be extracted automatically via dependency parsing. For six samples of the German learner corpus MERLIN (one per proficiency level), we found that in spite of many ungrammatical sentences in texts of low proficiency levels, human annotators find only few true ambiguities that would make the extraction of NPs and their heads infeasible. The automatic parsers, however, perform rather poorly on extracting the relevant elements for texts on CEFR levels A1-B1 ({\textless} 70{\%}) but quite well from level B2 onwards ( 90{\%}). We discuss the sources of errors and how performance could potentially be increased in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laarmann-quante-etal-2024-automatic-extraction">
<titleInfo>
<title>Automatic Extraction of Nominal Phrases from German Learner Texts of Different Proficiency Levels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Müller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Belke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Correctly inflecting determiners and adjectives so that they agree with the noun in nominal phrases (NPs) is a big challenge for learners of German. Given the increasing number of available learner corpora, a large-scale corpus-based study on the acquisition of this aspect of German morphosyntax would be desirable. In this paper, we present a pilot study in which we investigate how well nouns, their grammatical heads and the dependents that have to agree with the noun can be extracted automatically via dependency parsing. For six samples of the German learner corpus MERLIN (one per proficiency level), we found that in spite of many ungrammatical sentences in texts of low proficiency levels, human annotators find only few true ambiguities that would make the extraction of NPs and their heads infeasible. The automatic parsers, however, perform rather poorly on extracting the relevant elements for texts on CEFR levels A1-B1 (\textless 70%) but quite well from level B2 onwards ( 90%). We discuss the sources of errors and how performance could potentially be increased in the future.</abstract>
<identifier type="citekey">laarmann-quante-etal-2024-automatic-extraction</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.172</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1925</start>
<end>1931</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Extraction of Nominal Phrases from German Learner Texts of Different Proficiency Levels
%A Laarmann-Quante, Ronja
%A Müller, Marco
%A Belke, Eva
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F laarmann-quante-etal-2024-automatic-extraction
%X Correctly inflecting determiners and adjectives so that they agree with the noun in nominal phrases (NPs) is a big challenge for learners of German. Given the increasing number of available learner corpora, a large-scale corpus-based study on the acquisition of this aspect of German morphosyntax would be desirable. In this paper, we present a pilot study in which we investigate how well nouns, their grammatical heads and the dependents that have to agree with the noun can be extracted automatically via dependency parsing. For six samples of the German learner corpus MERLIN (one per proficiency level), we found that in spite of many ungrammatical sentences in texts of low proficiency levels, human annotators find only few true ambiguities that would make the extraction of NPs and their heads infeasible. The automatic parsers, however, perform rather poorly on extracting the relevant elements for texts on CEFR levels A1-B1 (\textless 70%) but quite well from level B2 onwards ( 90%). We discuss the sources of errors and how performance could potentially be increased in the future.
%U https://aclanthology.org/2024.lrec-main.172
%P 1925-1931
Markdown (Informal)
[Automatic Extraction of Nominal Phrases from German Learner Texts of Different Proficiency Levels](https://aclanthology.org/2024.lrec-main.172) (Laarmann-Quante et al., LREC-COLING 2024)
ACL