@inproceedings{abdulrahman-etal-2019-developing,
title = "Developing a Fine-grained Corpus for a Less-resourced Language: the case of {K}urdish",
author = "Abdulrahman, Roshna and
Hassani, Hossein and
Ahmadi, Sina",
editor = "Axelrod, Amittai and
Yang, Diyi and
Cunha, Rossana and
Shaikh, Samira and
Waseem, Zeerak",
booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3634",
pages = "106--109",
abstract = "Kurdish is a less-resourced language consisting of different dialects written in various scripts. Approximately 30 million people in different countries speak the language. The lack of corpora is one of the main obstacles in Kurdish language processing. In this paper, we present KTC-the Kurdish Textbooks Corpus, which is composed of 31 K-12 textbooks in Sorani dialect. The corpus is normalized and categorized into 12 educational subjects containing 693,800 tokens (110,297 types). Our resource is publicly available for non-commercial use under the CC BY-NC-SA 4.0 license.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdulrahman-etal-2019-developing">
<titleInfo>
<title>Developing a Fine-grained Corpus for a Less-resourced Language: the case of Kurdish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roshna</namePart>
<namePart type="family">Abdulrahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Hassani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Workshop on Widening NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amittai</namePart>
<namePart type="family">Axelrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Zeerak</namePart>
<namePart type="family">Waseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Kurdish is a less-resourced language consisting of different dialects written in various scripts. Approximately 30 million people in different countries speak the language. The lack of corpora is one of the main obstacles in Kurdish language processing. In this paper, we present KTC-the Kurdish Textbooks Corpus, which is composed of 31 K-12 textbooks in Sorani dialect. The corpus is normalized and categorized into 12 educational subjects containing 693,800 tokens (110,297 types). Our resource is publicly available for non-commercial use under the CC BY-NC-SA 4.0 license.</abstract>
<identifier type="citekey">abdulrahman-etal-2019-developing</identifier>
<location>
<url>https://aclanthology.org/W19-3634</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>106</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a Fine-grained Corpus for a Less-resourced Language: the case of Kurdish
%A Abdulrahman, Roshna
%A Hassani, Hossein
%A Ahmadi, Sina
%Y Axelrod, Amittai
%Y Yang, Diyi
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Waseem, Zeerak
%S Proceedings of the 2019 Workshop on Widening NLP
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F abdulrahman-etal-2019-developing
%X Kurdish is a less-resourced language consisting of different dialects written in various scripts. Approximately 30 million people in different countries speak the language. The lack of corpora is one of the main obstacles in Kurdish language processing. In this paper, we present KTC-the Kurdish Textbooks Corpus, which is composed of 31 K-12 textbooks in Sorani dialect. The corpus is normalized and categorized into 12 educational subjects containing 693,800 tokens (110,297 types). Our resource is publicly available for non-commercial use under the CC BY-NC-SA 4.0 license.
%U https://aclanthology.org/W19-3634
%P 106-109
Markdown (Informal)
[Developing a Fine-grained Corpus for a Less-resourced Language: the case of Kurdish](https://aclanthology.org/W19-3634) (Abdulrahman et al., WiNLP 2019)
ACL