@inproceedings{heil-etal-2022-lsx,
title = "{LSX}{\_}team5 at {S}em{E}val-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover{'}s Distance",
author = "Heil, Stefan and
Kopp, Karina and
Zehe, Albin and
Kobs, Konstantin and
Hotho, Andreas",
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-1.168",
doi = "10.18653/v1/2022.semeval-1.168",
pages = "1190--1195",
abstract = "This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity. The task of the competition consisted of the development of a model, capable of determining the similarity between pairs of multilingual news articles. To address this challenge, we evaluated the Word Mover{'}s Distance in conjunction with word embeddings from ConceptNet Numberbatch and term frequencies of WorldLex, as well the Sentence Mover{'}s Distance based on sentence embeddings generated by pretrained transformer models of Sentence-BERT. To facilitate the comparison of multilingual articles with Sentence-BERT models, we deployed a Neural Machine Translation system. All our models achieve stable results in multilingual similarity estimation without learning parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heil-etal-2022-lsx">
<titleInfo>
<title>LSX_team5 at SemEval-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover’s Distance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Heil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karina</namePart>
<namePart type="family">Kopp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albin</namePart>
<namePart type="family">Zehe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Kobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Hotho</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>This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity. The task of the competition consisted of the development of a model, capable of determining the similarity between pairs of multilingual news articles. To address this challenge, we evaluated the Word Mover’s Distance in conjunction with word embeddings from ConceptNet Numberbatch and term frequencies of WorldLex, as well the Sentence Mover’s Distance based on sentence embeddings generated by pretrained transformer models of Sentence-BERT. To facilitate the comparison of multilingual articles with Sentence-BERT models, we deployed a Neural Machine Translation system. All our models achieve stable results in multilingual similarity estimation without learning parameters.</abstract>
<identifier type="citekey">heil-etal-2022-lsx</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.168</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.168</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1190</start>
<end>1195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LSX_team5 at SemEval-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover’s Distance
%A Heil, Stefan
%A Kopp, Karina
%A Zehe, Albin
%A Kobs, Konstantin
%A Hotho, Andreas
%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 heil-etal-2022-lsx
%X This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity. The task of the competition consisted of the development of a model, capable of determining the similarity between pairs of multilingual news articles. To address this challenge, we evaluated the Word Mover’s Distance in conjunction with word embeddings from ConceptNet Numberbatch and term frequencies of WorldLex, as well the Sentence Mover’s Distance based on sentence embeddings generated by pretrained transformer models of Sentence-BERT. To facilitate the comparison of multilingual articles with Sentence-BERT models, we deployed a Neural Machine Translation system. All our models achieve stable results in multilingual similarity estimation without learning parameters.
%R 10.18653/v1/2022.semeval-1.168
%U https://aclanthology.org/2022.semeval-1.168
%U https://doi.org/10.18653/v1/2022.semeval-1.168
%P 1190-1195
Markdown (Informal)
[LSX_team5 at SemEval-2022 Task 8: Multilingual News Article Similarity Assessment based on Word- and Sentence Mover’s Distance](https://aclanthology.org/2022.semeval-1.168) (Heil et al., SemEval 2022)
ACL