@inproceedings{piskorski-etal-2021-exploring,
title = "Exploring Linguistically-Lightweight Keyword Extraction Techniques for Indexing News Articles in a Multilingual Set-up",
author = "Piskorski, Jakub and
Stefanovitch, Nicolas and
Jacquet, Guillaume and
Podavini, Aldo",
editor = "Toivonen, Hannu and
Boggia, Michele",
booktitle = "Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.hackashop-1.6",
pages = "35--44",
abstract = "This paper presents a study of state-of-the-art unsupervised and linguistically unsophisticated keyword extraction algorithms, based on statistic-, graph-, and embedding-based approaches, including, i.a., Total Keyword Frequency, TF-IDF, RAKE, KPMiner, YAKE, KeyBERT, and variants of TextRank-based keyword extraction algorithms. The study was motivated by the need to select the most appropriate technique to extract keywords for indexing news articles in a real-world large-scale news analysis engine. The algorithms were evaluated on a corpus of circa 330 news articles in 7 languages. The overall best F1 scores for all languages on average were obtained using a combination of the recently introduced YAKE algorithm and KPMiner (20.1{\%}, 46.6{\%} and 47.2{\%} for exact, partial and fuzzy matching resp.).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="piskorski-etal-2021-exploring">
<titleInfo>
<title>Exploring Linguistically-Lightweight Keyword Extraction Techniques for Indexing News Articles in a Multilingual Set-up</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Stefanovitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Jacquet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Podavini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannu</namePart>
<namePart type="family">Toivonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Boggia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a study of state-of-the-art unsupervised and linguistically unsophisticated keyword extraction algorithms, based on statistic-, graph-, and embedding-based approaches, including, i.a., Total Keyword Frequency, TF-IDF, RAKE, KPMiner, YAKE, KeyBERT, and variants of TextRank-based keyword extraction algorithms. The study was motivated by the need to select the most appropriate technique to extract keywords for indexing news articles in a real-world large-scale news analysis engine. The algorithms were evaluated on a corpus of circa 330 news articles in 7 languages. The overall best F1 scores for all languages on average were obtained using a combination of the recently introduced YAKE algorithm and KPMiner (20.1%, 46.6% and 47.2% for exact, partial and fuzzy matching resp.).</abstract>
<identifier type="citekey">piskorski-etal-2021-exploring</identifier>
<location>
<url>https://aclanthology.org/2021.hackashop-1.6</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>35</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Linguistically-Lightweight Keyword Extraction Techniques for Indexing News Articles in a Multilingual Set-up
%A Piskorski, Jakub
%A Stefanovitch, Nicolas
%A Jacquet, Guillaume
%A Podavini, Aldo
%Y Toivonen, Hannu
%Y Boggia, Michele
%S Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F piskorski-etal-2021-exploring
%X This paper presents a study of state-of-the-art unsupervised and linguistically unsophisticated keyword extraction algorithms, based on statistic-, graph-, and embedding-based approaches, including, i.a., Total Keyword Frequency, TF-IDF, RAKE, KPMiner, YAKE, KeyBERT, and variants of TextRank-based keyword extraction algorithms. The study was motivated by the need to select the most appropriate technique to extract keywords for indexing news articles in a real-world large-scale news analysis engine. The algorithms were evaluated on a corpus of circa 330 news articles in 7 languages. The overall best F1 scores for all languages on average were obtained using a combination of the recently introduced YAKE algorithm and KPMiner (20.1%, 46.6% and 47.2% for exact, partial and fuzzy matching resp.).
%U https://aclanthology.org/2021.hackashop-1.6
%P 35-44
Markdown (Informal)
[Exploring Linguistically-Lightweight Keyword Extraction Techniques for Indexing News Articles in a Multilingual Set-up](https://aclanthology.org/2021.hackashop-1.6) (Piskorski et al., Hackashop 2021)
ACL
