@inproceedings{engelmann-etal-2024-arts,
title = "{ARTS}: Assessing Readability {\&} Text Simplicity",
author = {Engelmann, Bj{\"o}rn and
Kreutz, Christin Katharina and
Haak, Fabian and
Schaer, Philipp},
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.877/",
doi = "10.18653/v1/2024.findings-emnlp.877",
pages = "14925--14942",
abstract = "Automatic text simplification aims to reduce a text{'}s complexity. Its evaluation should quantify how easy it is to understand a text. Datasets with simplicity labels on text level are a prerequisite for developing such evaluation approaches. However, current publicly available datasets do not align with this, as they mainly treat text simplification as a relational concept ({``}How much simpler has this text gotten compared to the original version?'') or assign discrete readability levels.This work alleviates the problem of Assessing Readability {\&} Text Simplicity. We present ARTS, a method for language-independent construction of datasets for simplicity assessment. We propose using pairwise comparisons of texts in conjunction with an Elo algorithm to produce a simplicity ranking and simplicity scores. Additionally, we provide a high-quality human-labeled and three GPT-labeled simplicity datasets. Our results show a high correlation between human and LLM-based labels, allowing for an effective and cost-efficient way to construct large synthetic datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="engelmann-etal-2024-arts">
<titleInfo>
<title>ARTS: Assessing Readability & Text Simplicity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Engelmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christin</namePart>
<namePart type="given">Katharina</namePart>
<namePart type="family">Kreutz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Haak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Schaer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic text simplification aims to reduce a text’s complexity. Its evaluation should quantify how easy it is to understand a text. Datasets with simplicity labels on text level are a prerequisite for developing such evaluation approaches. However, current publicly available datasets do not align with this, as they mainly treat text simplification as a relational concept (“How much simpler has this text gotten compared to the original version?”) or assign discrete readability levels.This work alleviates the problem of Assessing Readability & Text Simplicity. We present ARTS, a method for language-independent construction of datasets for simplicity assessment. We propose using pairwise comparisons of texts in conjunction with an Elo algorithm to produce a simplicity ranking and simplicity scores. Additionally, we provide a high-quality human-labeled and three GPT-labeled simplicity datasets. Our results show a high correlation between human and LLM-based labels, allowing for an effective and cost-efficient way to construct large synthetic datasets.</abstract>
<identifier type="citekey">engelmann-etal-2024-arts</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.877</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.877/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>14925</start>
<end>14942</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARTS: Assessing Readability & Text Simplicity
%A Engelmann, Björn
%A Kreutz, Christin Katharina
%A Haak, Fabian
%A Schaer, Philipp
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F engelmann-etal-2024-arts
%X Automatic text simplification aims to reduce a text’s complexity. Its evaluation should quantify how easy it is to understand a text. Datasets with simplicity labels on text level are a prerequisite for developing such evaluation approaches. However, current publicly available datasets do not align with this, as they mainly treat text simplification as a relational concept (“How much simpler has this text gotten compared to the original version?”) or assign discrete readability levels.This work alleviates the problem of Assessing Readability & Text Simplicity. We present ARTS, a method for language-independent construction of datasets for simplicity assessment. We propose using pairwise comparisons of texts in conjunction with an Elo algorithm to produce a simplicity ranking and simplicity scores. Additionally, we provide a high-quality human-labeled and three GPT-labeled simplicity datasets. Our results show a high correlation between human and LLM-based labels, allowing for an effective and cost-efficient way to construct large synthetic datasets.
%R 10.18653/v1/2024.findings-emnlp.877
%U https://aclanthology.org/2024.findings-emnlp.877/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.877
%P 14925-14942
Markdown (Informal)
[ARTS: Assessing Readability & Text Simplicity](https://aclanthology.org/2024.findings-emnlp.877/) (Engelmann et al., Findings 2024)
ACL
- Björn Engelmann, Christin Katharina Kreutz, Fabian Haak, and Philipp Schaer. 2024. ARTS: Assessing Readability & Text Simplicity. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14925–14942, Miami, Florida, USA. Association for Computational Linguistics.