@inproceedings{qasmi-etal-2020-simplifyur,
title = "{S}implify{UR}: Unsupervised Lexical Text Simplification for {U}rdu",
author = "Qasmi, Namoos Hayat and
Zia, Haris Bin and
Athar, Awais and
Raza, Agha Ali",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.428",
pages = "3484--3489",
abstract = "This paper presents the first attempt at Automatic Text Simplification (ATS) for Urdu, the language of 170 million people worldwide. Being a low-resource language in terms of standard linguistic resources, recent text simplification approaches that rely on manually crafted simplified corpora or lexicons such as WordNet are not applicable to Urdu. Urdu is a morphologically rich language that requires unique considerations such as proper handling of inflectional case and honorifics. We present an unsupervised method for lexical simplification of complex Urdu text. Our method only requires plain Urdu text and makes use of word embeddings together with a set of morphological features to generate simplifications. Our system achieves a BLEU score of 80.15 and SARI score of 42.02 upon automatic evaluation on manually crafted simplified corpora. We also report results for human evaluations for correctness, grammaticality, meaning-preservation and simplicity of the output. Our code and corpus are publicly available to make our results reproducible.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qasmi-etal-2020-simplifyur">
<titleInfo>
<title>SimplifyUR: Unsupervised Lexical Text Simplification for Urdu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Namoos</namePart>
<namePart type="given">Hayat</namePart>
<namePart type="family">Qasmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haris</namePart>
<namePart type="given">Bin</namePart>
<namePart type="family">Zia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Awais</namePart>
<namePart type="family">Athar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agha</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Raza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper presents the first attempt at Automatic Text Simplification (ATS) for Urdu, the language of 170 million people worldwide. Being a low-resource language in terms of standard linguistic resources, recent text simplification approaches that rely on manually crafted simplified corpora or lexicons such as WordNet are not applicable to Urdu. Urdu is a morphologically rich language that requires unique considerations such as proper handling of inflectional case and honorifics. We present an unsupervised method for lexical simplification of complex Urdu text. Our method only requires plain Urdu text and makes use of word embeddings together with a set of morphological features to generate simplifications. Our system achieves a BLEU score of 80.15 and SARI score of 42.02 upon automatic evaluation on manually crafted simplified corpora. We also report results for human evaluations for correctness, grammaticality, meaning-preservation and simplicity of the output. Our code and corpus are publicly available to make our results reproducible.</abstract>
<identifier type="citekey">qasmi-etal-2020-simplifyur</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.428</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3484</start>
<end>3489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SimplifyUR: Unsupervised Lexical Text Simplification for Urdu
%A Qasmi, Namoos Hayat
%A Zia, Haris Bin
%A Athar, Awais
%A Raza, Agha Ali
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F qasmi-etal-2020-simplifyur
%X This paper presents the first attempt at Automatic Text Simplification (ATS) for Urdu, the language of 170 million people worldwide. Being a low-resource language in terms of standard linguistic resources, recent text simplification approaches that rely on manually crafted simplified corpora or lexicons such as WordNet are not applicable to Urdu. Urdu is a morphologically rich language that requires unique considerations such as proper handling of inflectional case and honorifics. We present an unsupervised method for lexical simplification of complex Urdu text. Our method only requires plain Urdu text and makes use of word embeddings together with a set of morphological features to generate simplifications. Our system achieves a BLEU score of 80.15 and SARI score of 42.02 upon automatic evaluation on manually crafted simplified corpora. We also report results for human evaluations for correctness, grammaticality, meaning-preservation and simplicity of the output. Our code and corpus are publicly available to make our results reproducible.
%U https://aclanthology.org/2020.lrec-1.428
%P 3484-3489
Markdown (Informal)
[SimplifyUR: Unsupervised Lexical Text Simplification for Urdu](https://aclanthology.org/2020.lrec-1.428) (Qasmi et al., LREC 2020)
ACL