@inproceedings{shardlow-alva-manchego-2022-simple,
title = "Simple {TICO}-19: A Dataset for Joint Translation and Simplification of {COVID}-19 Texts",
author = "Shardlow, Matthew and
Alva-Manchego, Fernando",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.331",
pages = "3093--3102",
abstract = "Specialist high-quality information is typically first available in English, and it is written in a language that may be difficult to understand by most readers. While Machine Translation technologies contribute to mitigate the first issue, the translated content will most likely still contain complex language. In order to investigate and address both problems simultaneously, we introduce Simple TICO-19, a new language resource containing manual simplifications of the English and Spanish portions of the TICO-19 corpus for Machine Translation of COVID-19 literature. We provide an in-depth description of the annotation process, which entailed designing an annotation manual and employing four annotators (two native English speakers and two native Spanish speakers) who simplified over 6,000 sentences from the English and Spanish portions of the TICO-19 corpus. We report several statistics on the new dataset, focusing on analysing the improvements in readability from the original texts to their simplified versions. In addition, we propose baseline methodologies for automatically generating the simplifications, translations and joint translation and simplifications contained in our dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shardlow-alva-manchego-2022-simple">
<titleInfo>
<title>Simple TICO-19: A Dataset for Joint Translation and Simplification of COVID-19 Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Specialist high-quality information is typically first available in English, and it is written in a language that may be difficult to understand by most readers. While Machine Translation technologies contribute to mitigate the first issue, the translated content will most likely still contain complex language. In order to investigate and address both problems simultaneously, we introduce Simple TICO-19, a new language resource containing manual simplifications of the English and Spanish portions of the TICO-19 corpus for Machine Translation of COVID-19 literature. We provide an in-depth description of the annotation process, which entailed designing an annotation manual and employing four annotators (two native English speakers and two native Spanish speakers) who simplified over 6,000 sentences from the English and Spanish portions of the TICO-19 corpus. We report several statistics on the new dataset, focusing on analysing the improvements in readability from the original texts to their simplified versions. In addition, we propose baseline methodologies for automatically generating the simplifications, translations and joint translation and simplifications contained in our dataset.</abstract>
<identifier type="citekey">shardlow-alva-manchego-2022-simple</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.331</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3093</start>
<end>3102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple TICO-19: A Dataset for Joint Translation and Simplification of COVID-19 Texts
%A Shardlow, Matthew
%A Alva-Manchego, Fernando
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F shardlow-alva-manchego-2022-simple
%X Specialist high-quality information is typically first available in English, and it is written in a language that may be difficult to understand by most readers. While Machine Translation technologies contribute to mitigate the first issue, the translated content will most likely still contain complex language. In order to investigate and address both problems simultaneously, we introduce Simple TICO-19, a new language resource containing manual simplifications of the English and Spanish portions of the TICO-19 corpus for Machine Translation of COVID-19 literature. We provide an in-depth description of the annotation process, which entailed designing an annotation manual and employing four annotators (two native English speakers and two native Spanish speakers) who simplified over 6,000 sentences from the English and Spanish portions of the TICO-19 corpus. We report several statistics on the new dataset, focusing on analysing the improvements in readability from the original texts to their simplified versions. In addition, we propose baseline methodologies for automatically generating the simplifications, translations and joint translation and simplifications contained in our dataset.
%U https://aclanthology.org/2022.lrec-1.331
%P 3093-3102
Markdown (Informal)
[Simple TICO-19: A Dataset for Joint Translation and Simplification of COVID-19 Texts](https://aclanthology.org/2022.lrec-1.331) (Shardlow & Alva-Manchego, LREC 2022)
ACL