@inproceedings{ahmadi-etal-2020-corpus,
title = "A Corpus of the {S}orani {K}urdish Folkloric Lyrics",
author = "Ahmadi, Sina and
Hassani, Hossein and
Abedi, Kamaladdin",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.46",
pages = "330--335",
abstract = "Kurdish poetry and prose narratives were historically transmitted orally and less in a written form. Being an essential medium of oral narration and literature, Kurdish lyrics have had a unique attribute in becoming a vital resource for different types of studies, including Digital Humanities, Computational Folkloristics and Computational Linguistics. As an initial study of its kind for the Kurdish language, this paper presents our efforts in transcribing and collecting Kurdish folk lyrics as a corpus that covers various Kurdish musical genres, in particular Beyt, Gorani, Bend, and Heyran. We believe that this corpus contributes to Kurdish language processing in several ways, such as compensation for the lack of a long history of written text by incorporating oral literature, presenting an unexplored realm in Kurdish language processing, and assisting the initiation of Kurdish computational folkloristics. Our corpus contains 49,582 tokens in the Sorani dialect of Kurdish. The corpus is publicly available in the Text Encoding Initiative (TEI) format for non-commercial use.",
language = "English",
ISBN = "979-10-95546-35-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmadi-etal-2020-corpus">
<titleInfo>
<title>A Corpus of the Sorani Kurdish Folkloric Lyrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</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">Kamaladdin</namePart>
<namePart type="family">Abedi</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 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</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">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>Kurdish poetry and prose narratives were historically transmitted orally and less in a written form. Being an essential medium of oral narration and literature, Kurdish lyrics have had a unique attribute in becoming a vital resource for different types of studies, including Digital Humanities, Computational Folkloristics and Computational Linguistics. As an initial study of its kind for the Kurdish language, this paper presents our efforts in transcribing and collecting Kurdish folk lyrics as a corpus that covers various Kurdish musical genres, in particular Beyt, Gorani, Bend, and Heyran. We believe that this corpus contributes to Kurdish language processing in several ways, such as compensation for the lack of a long history of written text by incorporating oral literature, presenting an unexplored realm in Kurdish language processing, and assisting the initiation of Kurdish computational folkloristics. Our corpus contains 49,582 tokens in the Sorani dialect of Kurdish. The corpus is publicly available in the Text Encoding Initiative (TEI) format for non-commercial use.</abstract>
<identifier type="citekey">ahmadi-etal-2020-corpus</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.46</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>330</start>
<end>335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of the Sorani Kurdish Folkloric Lyrics
%A Ahmadi, Sina
%A Hassani, Hossein
%A Abedi, Kamaladdin
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G English
%F ahmadi-etal-2020-corpus
%X Kurdish poetry and prose narratives were historically transmitted orally and less in a written form. Being an essential medium of oral narration and literature, Kurdish lyrics have had a unique attribute in becoming a vital resource for different types of studies, including Digital Humanities, Computational Folkloristics and Computational Linguistics. As an initial study of its kind for the Kurdish language, this paper presents our efforts in transcribing and collecting Kurdish folk lyrics as a corpus that covers various Kurdish musical genres, in particular Beyt, Gorani, Bend, and Heyran. We believe that this corpus contributes to Kurdish language processing in several ways, such as compensation for the lack of a long history of written text by incorporating oral literature, presenting an unexplored realm in Kurdish language processing, and assisting the initiation of Kurdish computational folkloristics. Our corpus contains 49,582 tokens in the Sorani dialect of Kurdish. The corpus is publicly available in the Text Encoding Initiative (TEI) format for non-commercial use.
%U https://aclanthology.org/2020.sltu-1.46
%P 330-335
Markdown (Informal)
[A Corpus of the Sorani Kurdish Folkloric Lyrics](https://aclanthology.org/2020.sltu-1.46) (Ahmadi et al., SLTU 2020)
ACL
- Sina Ahmadi, Hossein Hassani, and Kamaladdin Abedi. 2020. A Corpus of the Sorani Kurdish Folkloric Lyrics. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), pages 330–335, Marseille, France. European Language Resources association.