@inproceedings{tardy-etal-2023-lc,
title = "{LC}-Score: Reference-less estimation of Text Comprehension Difficulty",
author = "Tardy, Paul and
Roze, Charlotte and
Poupet, Paul",
editor = "{\v{S}}tajner, Sanja and
Saggio, Horacio and
Shardlow, Matthew and
Alva-Manchego, Fernando",
booktitle = "Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.tsar-1.11/",
pages = "109--115",
abstract = "Being able to read and understand written text is critical in a digital era. However, studies shows that a large fraction of the population experiences comprehension issues. In this context, further initiatives in accessibility are required to improve the audience text comprehension. However, writers are hardly assisted nor encouraged to produce easy-to-understand content. Moreover, Automatic Text Simplification (ATS) model development suffers from the lack of metric to accurately estimate comprehension difficulty. We present LC-SCORE, a simple approach for training text comprehension metric for any text without reference i.e. predicting how easy to understand a given text is on a [0, 100] scale. Our objective with this scale is to quantitatively capture the extend to which a text suits to the Langage Clair (LC, Clear Language) guidelines, a French initiative closely related to English Plain Language. We explore two approaches: (i) using linguistically motivated indicators used to train statistical models, and (ii) neural learning directly from text leveraging pre-trained language models. We introduce a simple proxy task for comprehension difficulty training as a classification task. To evaluate our models, we run two distinct human annotation experiments, and find that both approaches (indicator based and neural) outperforms commonly used readability and comprehension metrics such as FKGL."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tardy-etal-2023-lc">
<titleInfo>
<title>LC-Score: Reference-less estimation of Text Comprehension Difficulty</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Tardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="family">Roze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Poupet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Štajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Being able to read and understand written text is critical in a digital era. However, studies shows that a large fraction of the population experiences comprehension issues. In this context, further initiatives in accessibility are required to improve the audience text comprehension. However, writers are hardly assisted nor encouraged to produce easy-to-understand content. Moreover, Automatic Text Simplification (ATS) model development suffers from the lack of metric to accurately estimate comprehension difficulty. We present LC-SCORE, a simple approach for training text comprehension metric for any text without reference i.e. predicting how easy to understand a given text is on a [0, 100] scale. Our objective with this scale is to quantitatively capture the extend to which a text suits to the Langage Clair (LC, Clear Language) guidelines, a French initiative closely related to English Plain Language. We explore two approaches: (i) using linguistically motivated indicators used to train statistical models, and (ii) neural learning directly from text leveraging pre-trained language models. We introduce a simple proxy task for comprehension difficulty training as a classification task. To evaluate our models, we run two distinct human annotation experiments, and find that both approaches (indicator based and neural) outperforms commonly used readability and comprehension metrics such as FKGL.</abstract>
<identifier type="citekey">tardy-etal-2023-lc</identifier>
<location>
<url>https://aclanthology.org/2023.tsar-1.11/</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>109</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LC-Score: Reference-less estimation of Text Comprehension Difficulty
%A Tardy, Paul
%A Roze, Charlotte
%A Poupet, Paul
%Y Štajner, Sanja
%Y Saggio, Horacio
%Y Shardlow, Matthew
%Y Alva-Manchego, Fernando
%S Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F tardy-etal-2023-lc
%X Being able to read and understand written text is critical in a digital era. However, studies shows that a large fraction of the population experiences comprehension issues. In this context, further initiatives in accessibility are required to improve the audience text comprehension. However, writers are hardly assisted nor encouraged to produce easy-to-understand content. Moreover, Automatic Text Simplification (ATS) model development suffers from the lack of metric to accurately estimate comprehension difficulty. We present LC-SCORE, a simple approach for training text comprehension metric for any text without reference i.e. predicting how easy to understand a given text is on a [0, 100] scale. Our objective with this scale is to quantitatively capture the extend to which a text suits to the Langage Clair (LC, Clear Language) guidelines, a French initiative closely related to English Plain Language. We explore two approaches: (i) using linguistically motivated indicators used to train statistical models, and (ii) neural learning directly from text leveraging pre-trained language models. We introduce a simple proxy task for comprehension difficulty training as a classification task. To evaluate our models, we run two distinct human annotation experiments, and find that both approaches (indicator based and neural) outperforms commonly used readability and comprehension metrics such as FKGL.
%U https://aclanthology.org/2023.tsar-1.11/
%P 109-115
Markdown (Informal)
[LC-Score: Reference-less estimation of Text Comprehension Difficulty](https://aclanthology.org/2023.tsar-1.11/) (Tardy et al., TSAR 2023)
ACL