@inproceedings{chen-etal-2022-semeval,
title = "{S}em{E}val-2022 Task 8: Multilingual news article similarity",
author = {Chen, Xi and
Zeynali, Ali and
Camargo, Chico and
Fl{\"o}ck, Fabian and
Gaffney, Devin and
Grabowicz, Przemyslaw and
Hale, Scott and
Jurgens, David and
Samory, Mattia},
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.155",
doi = "10.18653/v1/2022.semeval-1.155",
pages = "1094--1106",
abstract = "Thousands of new news articles appear daily in outlets in different languages. Understanding which articles refer to the same story can not only improve applications like news aggregation but enable cross-linguistic analysis of media consumption and attention. However, assessing the similarity of stories in news articles is challenging due to the different dimensions in which a story might vary, e.g., two articles may have substantial textual overlap but describe similar events that happened years apart. To address this challenge, we introduce a new dataset of nearly 10,000 news article pairs spanning 18 language combinations annotated for seven dimensions of similarity as SemEval 2022 Task 8. Here, we present an overview of the task, the best performing submissions, and the frontiers and challenges for measuring multilingual news article similarity. While the participants of this SemEval task contributed very strong models, achieving up to 0.818 correlation with gold standard labels across languages, human annotators are capable of reaching higher correlations, suggesting space for further progress.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-semeval">
<titleInfo>
<title>SemEval-2022 Task 8: Multilingual news article similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Zeynali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chico</namePart>
<namePart type="family">Camargo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Flöck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devin</namePart>
<namePart type="family">Gaffney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Przemyslaw</namePart>
<namePart type="family">Grabowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Hale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mattia</namePart>
<namePart type="family">Samory</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Thousands of new news articles appear daily in outlets in different languages. Understanding which articles refer to the same story can not only improve applications like news aggregation but enable cross-linguistic analysis of media consumption and attention. However, assessing the similarity of stories in news articles is challenging due to the different dimensions in which a story might vary, e.g., two articles may have substantial textual overlap but describe similar events that happened years apart. To address this challenge, we introduce a new dataset of nearly 10,000 news article pairs spanning 18 language combinations annotated for seven dimensions of similarity as SemEval 2022 Task 8. Here, we present an overview of the task, the best performing submissions, and the frontiers and challenges for measuring multilingual news article similarity. While the participants of this SemEval task contributed very strong models, achieving up to 0.818 correlation with gold standard labels across languages, human annotators are capable of reaching higher correlations, suggesting space for further progress.</abstract>
<identifier type="citekey">chen-etal-2022-semeval</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.155</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.155</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1094</start>
<end>1106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemEval-2022 Task 8: Multilingual news article similarity
%A Chen, Xi
%A Zeynali, Ali
%A Camargo, Chico
%A Flöck, Fabian
%A Gaffney, Devin
%A Grabowicz, Przemyslaw
%A Hale, Scott
%A Jurgens, David
%A Samory, Mattia
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F chen-etal-2022-semeval
%X Thousands of new news articles appear daily in outlets in different languages. Understanding which articles refer to the same story can not only improve applications like news aggregation but enable cross-linguistic analysis of media consumption and attention. However, assessing the similarity of stories in news articles is challenging due to the different dimensions in which a story might vary, e.g., two articles may have substantial textual overlap but describe similar events that happened years apart. To address this challenge, we introduce a new dataset of nearly 10,000 news article pairs spanning 18 language combinations annotated for seven dimensions of similarity as SemEval 2022 Task 8. Here, we present an overview of the task, the best performing submissions, and the frontiers and challenges for measuring multilingual news article similarity. While the participants of this SemEval task contributed very strong models, achieving up to 0.818 correlation with gold standard labels across languages, human annotators are capable of reaching higher correlations, suggesting space for further progress.
%R 10.18653/v1/2022.semeval-1.155
%U https://aclanthology.org/2022.semeval-1.155
%U https://doi.org/10.18653/v1/2022.semeval-1.155
%P 1094-1106
Markdown (Informal)
[SemEval-2022 Task 8: Multilingual news article similarity](https://aclanthology.org/2022.semeval-1.155) (Chen et al., SemEval 2022)
ACL
- Xi Chen, Ali Zeynali, Chico Camargo, Fabian Flöck, Devin Gaffney, Przemyslaw Grabowicz, Scott Hale, David Jurgens, and Mattia Samory. 2022. SemEval-2022 Task 8: Multilingual news article similarity. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1094–1106, Seattle, United States. Association for Computational Linguistics.