@inproceedings{yeshpanov-etal-2022-kaznerd,
title = "{K}az{NERD}: {K}azakh Named Entity Recognition Dataset",
author = "Yeshpanov, Rustem and
Khassanov, Yerbolat and
Varol, Huseyin Atakan",
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-1.44",
pages = "417--426",
abstract = "We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward{---}but rigorous{---}rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named entity recognition were also built, with the best-performing model achieving an exact match F1-score of 97.22{\%} on the test set. The annotated dataset, guidelines, and codes used to train the models are freely available for download under the CC BY 4.0 licence from \url{https://github.com/IS2AI/KazNERD}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yeshpanov-etal-2022-kaznerd">
<titleInfo>
<title>KazNERD: Kazakh Named Entity Recognition Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rustem</namePart>
<namePart type="family">Yeshpanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yerbolat</namePart>
<namePart type="family">Khassanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huseyin</namePart>
<namePart type="given">Atakan</namePart>
<namePart type="family">Varol</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>We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward—but rigorous—rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named entity recognition were also built, with the best-performing model achieving an exact match F1-score of 97.22% on the test set. The annotated dataset, guidelines, and codes used to train the models are freely available for download under the CC BY 4.0 licence from https://github.com/IS2AI/KazNERD.</abstract>
<identifier type="citekey">yeshpanov-etal-2022-kaznerd</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.44</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>417</start>
<end>426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KazNERD: Kazakh Named Entity Recognition Dataset
%A Yeshpanov, Rustem
%A Khassanov, Yerbolat
%A Varol, Huseyin Atakan
%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 yeshpanov-etal-2022-kaznerd
%X We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward—but rigorous—rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named entity recognition were also built, with the best-performing model achieving an exact match F1-score of 97.22% on the test set. The annotated dataset, guidelines, and codes used to train the models are freely available for download under the CC BY 4.0 licence from https://github.com/IS2AI/KazNERD.
%U https://aclanthology.org/2022.lrec-1.44
%P 417-426
Markdown (Informal)
[KazNERD: Kazakh Named Entity Recognition Dataset](https://aclanthology.org/2022.lrec-1.44) (Yeshpanov et al., LREC 2022)
ACL
- Rustem Yeshpanov, Yerbolat Khassanov, and Huseyin Atakan Varol. 2022. KazNERD: Kazakh Named Entity Recognition Dataset. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 417–426, Marseille, France. European Language Resources Association.