@inproceedings{malmasi-2016-subdialectal,
title = "Subdialectal Differences in {S}orani {K}urdish",
author = "Malmasi, Shervin",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Tan, Liling and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin},
booktitle = "Proceedings of the Third Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial3)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4812",
pages = "89--96",
abstract = "In this study we apply classification methods for detecting subdialectal differences in Sorani Kurdish texts produced in different regions, namely Iran and Iraq. As Sorani is a low-resource language, no corpus including texts from different regions was readily available. To this end, we identified data sources that could be leveraged for this task to create a dataset of 200,000 sentences. Using surface features, we attempted to classify Sorani subdialects, showing that sentences from news sources in Iraq and Iran are distinguishable with 96{\%} accuracy. This is the first preliminary study for a dialect that has not been widely studied in computational linguistics, evidencing the possible existence of distinct subdialects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malmasi-2016-subdialectal">
<titleInfo>
<title>Subdialectal Differences in Sorani Kurdish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</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">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study we apply classification methods for detecting subdialectal differences in Sorani Kurdish texts produced in different regions, namely Iran and Iraq. As Sorani is a low-resource language, no corpus including texts from different regions was readily available. To this end, we identified data sources that could be leveraged for this task to create a dataset of 200,000 sentences. Using surface features, we attempted to classify Sorani subdialects, showing that sentences from news sources in Iraq and Iran are distinguishable with 96% accuracy. This is the first preliminary study for a dialect that has not been widely studied in computational linguistics, evidencing the possible existence of distinct subdialects.</abstract>
<identifier type="citekey">malmasi-2016-subdialectal</identifier>
<location>
<url>https://aclanthology.org/W16-4812</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>89</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subdialectal Differences in Sorani Kurdish
%A Malmasi, Shervin
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Tan, Liling
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%S Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F malmasi-2016-subdialectal
%X In this study we apply classification methods for detecting subdialectal differences in Sorani Kurdish texts produced in different regions, namely Iran and Iraq. As Sorani is a low-resource language, no corpus including texts from different regions was readily available. To this end, we identified data sources that could be leveraged for this task to create a dataset of 200,000 sentences. Using surface features, we attempted to classify Sorani subdialects, showing that sentences from news sources in Iraq and Iran are distinguishable with 96% accuracy. This is the first preliminary study for a dialect that has not been widely studied in computational linguistics, evidencing the possible existence of distinct subdialects.
%U https://aclanthology.org/W16-4812
%P 89-96
Markdown (Informal)
[Subdialectal Differences in Sorani Kurdish](https://aclanthology.org/W16-4812) (Malmasi, VarDial 2016)
ACL
- Shervin Malmasi. 2016. Subdialectal Differences in Sorani Kurdish. In Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3), pages 89–96, Osaka, Japan. The COLING 2016 Organizing Committee.