@inproceedings{verma-etal-2022-maked,
title = "{MAKED}: Multi-lingual Automatic Keyword Extraction Dataset",
author = "Verma, Yash and
Jangra, Anubhav and
Saha, Sriparna and
Jatowt, Adam and
Roy, Dwaipayan",
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-1.664",
pages = "6170--6179",
abstract = "Keyword extraction is an integral task for many downstream problems like clustering, recommendation, search and classification. Development and evaluation of keyword extraction techniques require an exhaustive dataset; however, currently, the community lacks large-scale multi-lingual datasets. In this paper, we present MAKED, a large-scale multi-lingual keyword extraction dataset comprising of 540K+ news articles from British Broadcasting Corporation News (BBC News) spanning 20 languages. It is the first keyword extraction dataset for 11 of these 20 languages. The quality of the dataset is examined by experimentation with several baselines. We believe that the proposed dataset will help advance the field of automatic keyword extraction given its size, diversity in terms of languages used, topics covered and time periods as well as its focus on under-studied languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verma-etal-2022-maked">
<titleInfo>
<title>MAKED: Multi-lingual Automatic Keyword Extraction Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubhav</namePart>
<namePart type="family">Jangra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Jatowt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dwaipayan</namePart>
<namePart type="family">Roy</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>Keyword extraction is an integral task for many downstream problems like clustering, recommendation, search and classification. Development and evaluation of keyword extraction techniques require an exhaustive dataset; however, currently, the community lacks large-scale multi-lingual datasets. In this paper, we present MAKED, a large-scale multi-lingual keyword extraction dataset comprising of 540K+ news articles from British Broadcasting Corporation News (BBC News) spanning 20 languages. It is the first keyword extraction dataset for 11 of these 20 languages. The quality of the dataset is examined by experimentation with several baselines. We believe that the proposed dataset will help advance the field of automatic keyword extraction given its size, diversity in terms of languages used, topics covered and time periods as well as its focus on under-studied languages.</abstract>
<identifier type="citekey">verma-etal-2022-maked</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.664</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6170</start>
<end>6179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAKED: Multi-lingual Automatic Keyword Extraction Dataset
%A Verma, Yash
%A Jangra, Anubhav
%A Saha, Sriparna
%A Jatowt, Adam
%A Roy, Dwaipayan
%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 verma-etal-2022-maked
%X Keyword extraction is an integral task for many downstream problems like clustering, recommendation, search and classification. Development and evaluation of keyword extraction techniques require an exhaustive dataset; however, currently, the community lacks large-scale multi-lingual datasets. In this paper, we present MAKED, a large-scale multi-lingual keyword extraction dataset comprising of 540K+ news articles from British Broadcasting Corporation News (BBC News) spanning 20 languages. It is the first keyword extraction dataset for 11 of these 20 languages. The quality of the dataset is examined by experimentation with several baselines. We believe that the proposed dataset will help advance the field of automatic keyword extraction given its size, diversity in terms of languages used, topics covered and time periods as well as its focus on under-studied languages.
%U https://aclanthology.org/2022.lrec-1.664
%P 6170-6179
Markdown (Informal)
[MAKED: Multi-lingual Automatic Keyword Extraction Dataset](https://aclanthology.org/2022.lrec-1.664) (Verma et al., LREC 2022)
ACL
- Yash Verma, Anubhav Jangra, Sriparna Saha, Adam Jatowt, and Dwaipayan Roy. 2022. MAKED: Multi-lingual Automatic Keyword Extraction Dataset. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6170–6179, Marseille, France. European Language Resources Association.