@inproceedings{gonzalez-dios-etal-2022-irekialfes,
title = "{I}rekia{LF}es: a New Open Benchmark and Baseline Systems for {S}panish Automatic Text Simplification",
author = "Gonzalez-Dios, Itziar and
Guti{\'e}rrez-Fandi{\~n}o, Iker and
Cumbicus-Pineda, Oscar m. and
Soroa, Aitor",
editor = "{\v{S}}tajner, Sanja and
Saggion, Horacio and
Ferr{\'e}s, Daniel and
Shardlow, Matthew and
Sheang, Kim Cheng and
North, Kai and
Zampieri, Marcos and
Xu, Wei",
booktitle = "Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.tsar-1.8",
doi = "10.18653/v1/2022.tsar-1.8",
pages = "86--97",
abstract = "Automatic Text simplification (ATS) seeks to reduce the complexity of a text for a general public or a target audience. In the last years, deep learning methods have become the most used systems in ATS research, but these systems need large and good quality datasets to be evaluated. Moreover, these data are available on a large scale only for English and in some cases with restrictive licenses. In this paper, we present IrekiaLF{\_}es, an open-license benchmark for Spanish text simplification. It consists of a document-level corpus and a sentence-level test set that has been manually aligned. We also conduct a neurolinguistically-based evaluation of the corpus in order to reveal its suitability for text simplification. This evaluation follows the Lexicon-Unification-Linearity (LeULi) model of neurolinguistic complexity assessment. Finally, we present a set of experiments and baselines of ATS systems in a zero-shot scenario.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-dios-etal-2022-irekialfes">
<titleInfo>
<title>IrekiaLFes: a New Open Benchmark and Baseline Systems for Spanish Automatic Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Itziar</namePart>
<namePart type="family">Gonzalez-Dios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iker</namePart>
<namePart type="family">Gutiérrez-Fandiño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="given">m</namePart>
<namePart type="family">Cumbicus-Pineda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)</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">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ferrés</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">Kim</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Sheang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Text simplification (ATS) seeks to reduce the complexity of a text for a general public or a target audience. In the last years, deep learning methods have become the most used systems in ATS research, but these systems need large and good quality datasets to be evaluated. Moreover, these data are available on a large scale only for English and in some cases with restrictive licenses. In this paper, we present IrekiaLF_es, an open-license benchmark for Spanish text simplification. It consists of a document-level corpus and a sentence-level test set that has been manually aligned. We also conduct a neurolinguistically-based evaluation of the corpus in order to reveal its suitability for text simplification. This evaluation follows the Lexicon-Unification-Linearity (LeULi) model of neurolinguistic complexity assessment. Finally, we present a set of experiments and baselines of ATS systems in a zero-shot scenario.</abstract>
<identifier type="citekey">gonzalez-dios-etal-2022-irekialfes</identifier>
<identifier type="doi">10.18653/v1/2022.tsar-1.8</identifier>
<location>
<url>https://aclanthology.org/2022.tsar-1.8</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>86</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IrekiaLFes: a New Open Benchmark and Baseline Systems for Spanish Automatic Text Simplification
%A Gonzalez-Dios, Itziar
%A Gutiérrez-Fandiño, Iker
%A Cumbicus-Pineda, Oscar m.
%A Soroa, Aitor
%Y Štajner, Sanja
%Y Saggion, Horacio
%Y Ferrés, Daniel
%Y Shardlow, Matthew
%Y Sheang, Kim Cheng
%Y North, Kai
%Y Zampieri, Marcos
%Y Xu, Wei
%S Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Virtual)
%F gonzalez-dios-etal-2022-irekialfes
%X Automatic Text simplification (ATS) seeks to reduce the complexity of a text for a general public or a target audience. In the last years, deep learning methods have become the most used systems in ATS research, but these systems need large and good quality datasets to be evaluated. Moreover, these data are available on a large scale only for English and in some cases with restrictive licenses. In this paper, we present IrekiaLF_es, an open-license benchmark for Spanish text simplification. It consists of a document-level corpus and a sentence-level test set that has been manually aligned. We also conduct a neurolinguistically-based evaluation of the corpus in order to reveal its suitability for text simplification. This evaluation follows the Lexicon-Unification-Linearity (LeULi) model of neurolinguistic complexity assessment. Finally, we present a set of experiments and baselines of ATS systems in a zero-shot scenario.
%R 10.18653/v1/2022.tsar-1.8
%U https://aclanthology.org/2022.tsar-1.8
%U https://doi.org/10.18653/v1/2022.tsar-1.8
%P 86-97
Markdown (Informal)
[IrekiaLFes: a New Open Benchmark and Baseline Systems for Spanish Automatic Text Simplification](https://aclanthology.org/2022.tsar-1.8) (Gonzalez-Dios et al., TSAR 2022)
ACL