@inproceedings{miyata-etal-2025-unsupervised,
title = "Unsupervised Sentence Readability Estimation Based on Parallel Corpora for Text Simplification",
author = "Miyata, Rina and
Urakawa, Toru and
Tamori, Hideaki and
Kajiwara, Tomoyuki",
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-1.36/",
doi = "10.18653/v1/2025.bea-1.36",
pages = "499--504",
ISBN = "979-8-89176-270-1",
abstract = "We train a relative sentence readability estimator from a corpus without absolute sentence readability.Since sentence readability depends on the reader{'}s knowledge, objective and absolute readability assessments require costly annotation by experts.Therefore, few corpora have absolute sentence readability, while parallel corpora for text simplification with relative sentence readability between two sentences are available for many languages.With multilingual applications in mind, we propose a method to estimate relative sentence readability based on parallel corpora for text simplification.Experimental results on ranking a set of English sentences by readability show that our method outperforms existing unsupervised methods and is comparable to supervised methods based on absolute sentence readability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miyata-etal-2025-unsupervised">
<titleInfo>
<title>Unsupervised Sentence Readability Estimation Based on Parallel Corpora for Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rina</namePart>
<namePart type="family">Miyata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toru</namePart>
<namePart type="family">Urakawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideaki</namePart>
<namePart type="family">Tamori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</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 train a relative sentence readability estimator from a corpus without absolute sentence readability.Since sentence readability depends on the reader’s knowledge, objective and absolute readability assessments require costly annotation by experts.Therefore, few corpora have absolute sentence readability, while parallel corpora for text simplification with relative sentence readability between two sentences are available for many languages.With multilingual applications in mind, we propose a method to estimate relative sentence readability based on parallel corpora for text simplification.Experimental results on ranking a set of English sentences by readability show that our method outperforms existing unsupervised methods and is comparable to supervised methods based on absolute sentence readability.</abstract>
<identifier type="citekey">miyata-etal-2025-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.36</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.36/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>499</start>
<end>504</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Sentence Readability Estimation Based on Parallel Corpora for Text Simplification
%A Miyata, Rina
%A Urakawa, Toru
%A Tamori, Hideaki
%A Kajiwara, Tomoyuki
%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 miyata-etal-2025-unsupervised
%X We train a relative sentence readability estimator from a corpus without absolute sentence readability.Since sentence readability depends on the reader’s knowledge, objective and absolute readability assessments require costly annotation by experts.Therefore, few corpora have absolute sentence readability, while parallel corpora for text simplification with relative sentence readability between two sentences are available for many languages.With multilingual applications in mind, we propose a method to estimate relative sentence readability based on parallel corpora for text simplification.Experimental results on ranking a set of English sentences by readability show that our method outperforms existing unsupervised methods and is comparable to supervised methods based on absolute sentence readability.
%R 10.18653/v1/2025.bea-1.36
%U https://aclanthology.org/2025.bea-1.36/
%U https://doi.org/10.18653/v1/2025.bea-1.36
%P 499-504
Markdown (Informal)
[Unsupervised Sentence Readability Estimation Based on Parallel Corpora for Text Simplification](https://aclanthology.org/2025.bea-1.36/) (Miyata et al., BEA 2025)
ACL