@inproceedings{hartmann-etal-2020-simplex,
title = "{SIMPLEX}-{PB} 2.0: A Reliable Dataset for Lexical Simplification in {B}razilian {P}ortuguese",
author = "Hartmann, Nathan and
Paetzold, Gustavo Henrique and
Alu{\'\i}sio, Sandra",
editor = "Cunha, Rossana and
Shaikh, Samira and
Varis, Erika and
Georgi, Ryan and
Tsai, Alicia and
Anastasopoulos, Antonios and
Chandu, Khyathi Raghavi",
booktitle = "Proceedings of the Fourth Widening Natural Language Processing Workshop",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.winlp-1.6",
doi = "10.18653/v1/2020.winlp-1.6",
pages = "18--22",
abstract = "Most research on Lexical Simplification (LS) addresses non-native speakers of English, since they are numerous and easy to recruit. This makes it difficult to create LS solutions for other languages and target audiences. This paper presents SIMPLEX-PB 2.0, a dataset for LS in Brazilian Portuguese that, unlike its predecessor SIMPLEX-PB, accurately captures the needs of Brazilian underprivileged children. To create SIMPLEX-PB 2.0, we addressed all limitations of the old SIMPLEX-PB through multiple rounds of manual annotation. As a result, SIMPLEX-PB 2.0 features much more reliable and numerous candidate substitutions to complex words, as well as word complexity rankings produced by a group underprivileged children.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hartmann-etal-2020-simplex">
<titleInfo>
<title>SIMPLEX-PB 2.0: A Reliable Dataset for Lexical Simplification in Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Hartmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">Paetzold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Aluísio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Widening Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Varis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Georgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most research on Lexical Simplification (LS) addresses non-native speakers of English, since they are numerous and easy to recruit. This makes it difficult to create LS solutions for other languages and target audiences. This paper presents SIMPLEX-PB 2.0, a dataset for LS in Brazilian Portuguese that, unlike its predecessor SIMPLEX-PB, accurately captures the needs of Brazilian underprivileged children. To create SIMPLEX-PB 2.0, we addressed all limitations of the old SIMPLEX-PB through multiple rounds of manual annotation. As a result, SIMPLEX-PB 2.0 features much more reliable and numerous candidate substitutions to complex words, as well as word complexity rankings produced by a group underprivileged children.</abstract>
<identifier type="citekey">hartmann-etal-2020-simplex</identifier>
<identifier type="doi">10.18653/v1/2020.winlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2020.winlp-1.6</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>18</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SIMPLEX-PB 2.0: A Reliable Dataset for Lexical Simplification in Brazilian Portuguese
%A Hartmann, Nathan
%A Paetzold, Gustavo Henrique
%A Aluísio, Sandra
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Varis, Erika
%Y Georgi, Ryan
%Y Tsai, Alicia
%Y Anastasopoulos, Antonios
%Y Chandu, Khyathi Raghavi
%S Proceedings of the Fourth Widening Natural Language Processing Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F hartmann-etal-2020-simplex
%X Most research on Lexical Simplification (LS) addresses non-native speakers of English, since they are numerous and easy to recruit. This makes it difficult to create LS solutions for other languages and target audiences. This paper presents SIMPLEX-PB 2.0, a dataset for LS in Brazilian Portuguese that, unlike its predecessor SIMPLEX-PB, accurately captures the needs of Brazilian underprivileged children. To create SIMPLEX-PB 2.0, we addressed all limitations of the old SIMPLEX-PB through multiple rounds of manual annotation. As a result, SIMPLEX-PB 2.0 features much more reliable and numerous candidate substitutions to complex words, as well as word complexity rankings produced by a group underprivileged children.
%R 10.18653/v1/2020.winlp-1.6
%U https://aclanthology.org/2020.winlp-1.6
%U https://doi.org/10.18653/v1/2020.winlp-1.6
%P 18-22
Markdown (Informal)
[SIMPLEX-PB 2.0: A Reliable Dataset for Lexical Simplification in Brazilian Portuguese](https://aclanthology.org/2020.winlp-1.6) (Hartmann et al., WiNLP 2020)
ACL