@inproceedings{saggion-etal-2024-lexical,
title = "Lexical Complexity Prediction and Lexical Simplification for {C}atalan and {S}panish: Resource Creation, Quality Assessment, and Ethical Considerations",
author = "Saggion, Horacio and
Bott, Stefan and
Szasz, Sandra and
P{\'e}rez, Nelson and
Calder{\'o}n, Sa{\'u}l and
Sol{\'\i}s, Mart{\'\i}n",
editor = "Shardlow, Matthew and
Saggion, Horacio and
Alva-Manchego, Fernando and
Zampieri, Marcos and
North, Kai and
{\v{S}}tajner, Sanja and
Stodden, Regina",
booktitle = "Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.tsar-1.9",
pages = "82--94",
abstract = "Automatic lexical simplification is a task to substitute lexical items that may be unfamiliar and difficult to understand with easier and more common words. This paper presents the description and analysis of two novel datasets for lexical simplification in Spanish and Catalan. This dataset represents the first of its kind in Catalan and a substantial addition to the sparse data on automatic lexical simplification which is available for Spanish. Specifically, it is the first dataset for Spanish which includes scalar ratings of the understanding difficulty of lexical items. In addition, we present a detailed analysis aiming at assessing the appropriateness and ethical dimensions of the data for the lexical simplification task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saggion-etal-2024-lexical">
<titleInfo>
<title>Lexical Complexity Prediction and Lexical Simplification for Catalan and Spanish: Resource Creation, Quality Assessment, and Ethical Considerations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Bott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Szasz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="family">Pérez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saúl</namePart>
<namePart type="family">Calderón</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martín</namePart>
<namePart type="family">Solís</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>Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)</title>
</titleInfo>
<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">Horacio</namePart>
<namePart type="family">Saggion</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>
<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">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Regina</namePart>
<namePart type="family">Stodden</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 lexical simplification is a task to substitute lexical items that may be unfamiliar and difficult to understand with easier and more common words. This paper presents the description and analysis of two novel datasets for lexical simplification in Spanish and Catalan. This dataset represents the first of its kind in Catalan and a substantial addition to the sparse data on automatic lexical simplification which is available for Spanish. Specifically, it is the first dataset for Spanish which includes scalar ratings of the understanding difficulty of lexical items. In addition, we present a detailed analysis aiming at assessing the appropriateness and ethical dimensions of the data for the lexical simplification task.</abstract>
<identifier type="citekey">saggion-etal-2024-lexical</identifier>
<location>
<url>https://aclanthology.org/2024.tsar-1.9</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>82</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexical Complexity Prediction and Lexical Simplification for Catalan and Spanish: Resource Creation, Quality Assessment, and Ethical Considerations
%A Saggion, Horacio
%A Bott, Stefan
%A Szasz, Sandra
%A Pérez, Nelson
%A Calderón, Saúl
%A Solís, Martín
%Y Shardlow, Matthew
%Y Saggion, Horacio
%Y Alva-Manchego, Fernando
%Y Zampieri, Marcos
%Y North, Kai
%Y Štajner, Sanja
%Y Stodden, Regina
%S Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F saggion-etal-2024-lexical
%X Automatic lexical simplification is a task to substitute lexical items that may be unfamiliar and difficult to understand with easier and more common words. This paper presents the description and analysis of two novel datasets for lexical simplification in Spanish and Catalan. This dataset represents the first of its kind in Catalan and a substantial addition to the sparse data on automatic lexical simplification which is available for Spanish. Specifically, it is the first dataset for Spanish which includes scalar ratings of the understanding difficulty of lexical items. In addition, we present a detailed analysis aiming at assessing the appropriateness and ethical dimensions of the data for the lexical simplification task.
%U https://aclanthology.org/2024.tsar-1.9
%P 82-94
Markdown (Informal)
[Lexical Complexity Prediction and Lexical Simplification for Catalan and Spanish: Resource Creation, Quality Assessment, and Ethical Considerations](https://aclanthology.org/2024.tsar-1.9) (Saggion et al., TSAR 2024)
ACL
- Horacio Saggion, Stefan Bott, Sandra Szasz, Nelson Pérez, Saúl Calderón, and Martín Solís. 2024. Lexical Complexity Prediction and Lexical Simplification for Catalan and Spanish: Resource Creation, Quality Assessment, and Ethical Considerations. In Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024), pages 82–94, Miami, Florida, USA. Association for Computational Linguistics.