@inproceedings{drushchak-romanyshyn-2024-introducing,
title = "Introducing the Djinni Recruitment Dataset: A Corpus of Anonymized {CV}s and Job Postings",
author = "Drushchak, Nazarii and
Romanyshyn, Mariana",
editor = "Romanyshyn, Mariana and
Romanyshyn, Nataliia and
Hlybovets, Andrii and
Ignatenko, Oleksii",
booktitle = "Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.unlp-1.2",
pages = "8--13",
abstract = "This paper introduces the Djinni Recruitment Dataset, a large-scale open-source corpus of candidate profiles and job descriptions. With over 150,000 jobs and 230,000 candidates, the dataset includes samples in English and Ukrainian, thereby facilitating advancements in the recruitment domain of natural language processing (NLP) for both languages. It is one of the first open-source corpora in the recruitment domain, opening up new opportunities for AI-driven recruitment technologies and related fields. Notably, the dataset is accessible under the MIT license, encouraging widespread adoption for both scientific research and commercial projects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="drushchak-romanyshyn-2024-introducing">
<titleInfo>
<title>Introducing the Djinni Recruitment Dataset: A Corpus of Anonymized CVs and Job Postings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nazarii</namePart>
<namePart type="family">Drushchak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nataliia</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrii</namePart>
<namePart type="family">Hlybovets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleksii</namePart>
<namePart type="family">Ignatenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces the Djinni Recruitment Dataset, a large-scale open-source corpus of candidate profiles and job descriptions. With over 150,000 jobs and 230,000 candidates, the dataset includes samples in English and Ukrainian, thereby facilitating advancements in the recruitment domain of natural language processing (NLP) for both languages. It is one of the first open-source corpora in the recruitment domain, opening up new opportunities for AI-driven recruitment technologies and related fields. Notably, the dataset is accessible under the MIT license, encouraging widespread adoption for both scientific research and commercial projects.</abstract>
<identifier type="citekey">drushchak-romanyshyn-2024-introducing</identifier>
<location>
<url>https://aclanthology.org/2024.unlp-1.2</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing the Djinni Recruitment Dataset: A Corpus of Anonymized CVs and Job Postings
%A Drushchak, Nazarii
%A Romanyshyn, Mariana
%Y Romanyshyn, Mariana
%Y Romanyshyn, Nataliia
%Y Hlybovets, Andrii
%Y Ignatenko, Oleksii
%S Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F drushchak-romanyshyn-2024-introducing
%X This paper introduces the Djinni Recruitment Dataset, a large-scale open-source corpus of candidate profiles and job descriptions. With over 150,000 jobs and 230,000 candidates, the dataset includes samples in English and Ukrainian, thereby facilitating advancements in the recruitment domain of natural language processing (NLP) for both languages. It is one of the first open-source corpora in the recruitment domain, opening up new opportunities for AI-driven recruitment technologies and related fields. Notably, the dataset is accessible under the MIT license, encouraging widespread adoption for both scientific research and commercial projects.
%U https://aclanthology.org/2024.unlp-1.2
%P 8-13
Markdown (Informal)
[Introducing the Djinni Recruitment Dataset: A Corpus of Anonymized CVs and Job Postings](https://aclanthology.org/2024.unlp-1.2) (Drushchak & Romanyshyn, UNLP 2024)
ACL