@inproceedings{weiss-meurers-2022-assessing,
title = "Assessing sentence readability for {G}erman language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?",
author = "Weiss, Zarah and
Meurers, Detmar",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bea-1.19",
doi = "10.18653/v1/2022.bea-1.19",
pages = "141--153",
abstract = "We present a new state-of-the-art sentence-wise readability assessment model for German L2 readers. We build a linguistically broadly informed machine learning model and compare its performance against four commonly used readability formulas. To understand when the linguistic insights used to inform our model make a difference for readability assessment and when simple readability formulas suffice, we compare their performance based on two common automatic readability assessment tasks: predictive regression and sentence pair ranking. We find that leveraging linguistic insights yields top performances across tasks, but that for the identification of simplified sentences also readability formulas {--} which are easier to compute and more accessible {--} can be sufficiently precise. Linguistically informed modeling, however, is the only viable option for high quality outcomes in fine-grained prediction tasks. We then explore the sentence-wise readability profile of leveled texts written for language learners at a beginning, intermediate, and advanced level of German to showcase the valuable insights that sentence-wise readability assessment can have for the adaptation of learning materials and better understand how sentences{'} individual readability contributes to larger texts{'} overall readability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weiss-meurers-2022-assessing">
<titleInfo>
<title>Assessing sentence readability for German language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zarah</namePart>
<namePart type="family">Weiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Detmar</namePart>
<namePart type="family">Meurers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)</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">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">Nitin</namePart>
<namePart type="family">Madnani</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>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new state-of-the-art sentence-wise readability assessment model for German L2 readers. We build a linguistically broadly informed machine learning model and compare its performance against four commonly used readability formulas. To understand when the linguistic insights used to inform our model make a difference for readability assessment and when simple readability formulas suffice, we compare their performance based on two common automatic readability assessment tasks: predictive regression and sentence pair ranking. We find that leveraging linguistic insights yields top performances across tasks, but that for the identification of simplified sentences also readability formulas – which are easier to compute and more accessible – can be sufficiently precise. Linguistically informed modeling, however, is the only viable option for high quality outcomes in fine-grained prediction tasks. We then explore the sentence-wise readability profile of leveled texts written for language learners at a beginning, intermediate, and advanced level of German to showcase the valuable insights that sentence-wise readability assessment can have for the adaptation of learning materials and better understand how sentences’ individual readability contributes to larger texts’ overall readability.</abstract>
<identifier type="citekey">weiss-meurers-2022-assessing</identifier>
<identifier type="doi">10.18653/v1/2022.bea-1.19</identifier>
<location>
<url>https://aclanthology.org/2022.bea-1.19</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>141</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing sentence readability for German language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?
%A Weiss, Zarah
%A Meurers, Detmar
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F weiss-meurers-2022-assessing
%X We present a new state-of-the-art sentence-wise readability assessment model for German L2 readers. We build a linguistically broadly informed machine learning model and compare its performance against four commonly used readability formulas. To understand when the linguistic insights used to inform our model make a difference for readability assessment and when simple readability formulas suffice, we compare their performance based on two common automatic readability assessment tasks: predictive regression and sentence pair ranking. We find that leveraging linguistic insights yields top performances across tasks, but that for the identification of simplified sentences also readability formulas – which are easier to compute and more accessible – can be sufficiently precise. Linguistically informed modeling, however, is the only viable option for high quality outcomes in fine-grained prediction tasks. We then explore the sentence-wise readability profile of leveled texts written for language learners at a beginning, intermediate, and advanced level of German to showcase the valuable insights that sentence-wise readability assessment can have for the adaptation of learning materials and better understand how sentences’ individual readability contributes to larger texts’ overall readability.
%R 10.18653/v1/2022.bea-1.19
%U https://aclanthology.org/2022.bea-1.19
%U https://doi.org/10.18653/v1/2022.bea-1.19
%P 141-153
Markdown (Informal)
[Assessing sentence readability for German language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?](https://aclanthology.org/2022.bea-1.19) (Weiss & Meurers, BEA 2022)
ACL