@inproceedings{shushkevich-etal-2024-spiced-news,
title = "{SPICED}: News Similarity Detection Dataset with Multiple Topics and Complexity Levels",
author = "Shushkevich, Elena and
Mai, Long Thanh and
Loureiro, Manuel V. and
Derby, Steven and
Wijaya, Tri Kurniawan",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1320",
pages = "15181--15190",
abstract = "The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this requires the existence of topic-specific datasets, which are currently lacking. In this article, we propose a novel dataset of similar news, SPICED, which includes seven topics: Crime {\&} Law, Culture {\&} Entertainment, Disasters {\&} Accidents, Economy {\&} Business, Politics {\&} Conflicts, Science {\&} Technology, and Sports. Futhermore, we present four different levels of complexity, specifically designed for news similarity detection task. We benchmarked the created datasets using MinHash, BERT, SBERT, and SimCSE models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shushkevich-etal-2024-spiced-news">
<titleInfo>
<title>SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Shushkevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="given">Thanh</namePart>
<namePart type="family">Mai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Loureiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Derby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tri</namePart>
<namePart type="given">Kurniawan</namePart>
<namePart type="family">Wijaya</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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">Nianwen</namePart>
<namePart type="family">Xue</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>The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this requires the existence of topic-specific datasets, which are currently lacking. In this article, we propose a novel dataset of similar news, SPICED, which includes seven topics: Crime & Law, Culture & Entertainment, Disasters & Accidents, Economy & Business, Politics & Conflicts, Science & Technology, and Sports. Futhermore, we present four different levels of complexity, specifically designed for news similarity detection task. We benchmarked the created datasets using MinHash, BERT, SBERT, and SimCSE models.</abstract>
<identifier type="citekey">shushkevich-etal-2024-spiced-news</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1320</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15181</start>
<end>15190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels
%A Shushkevich, Elena
%A Mai, Long Thanh
%A Loureiro, Manuel V.
%A Derby, Steven
%A Wijaya, Tri Kurniawan
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shushkevich-etal-2024-spiced-news
%X The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this requires the existence of topic-specific datasets, which are currently lacking. In this article, we propose a novel dataset of similar news, SPICED, which includes seven topics: Crime & Law, Culture & Entertainment, Disasters & Accidents, Economy & Business, Politics & Conflicts, Science & Technology, and Sports. Futhermore, we present four different levels of complexity, specifically designed for news similarity detection task. We benchmarked the created datasets using MinHash, BERT, SBERT, and SimCSE models.
%U https://aclanthology.org/2024.lrec-main.1320
%P 15181-15190
Markdown (Informal)
[SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels](https://aclanthology.org/2024.lrec-main.1320) (Shushkevich et al., LREC-COLING 2024)
ACL