@inproceedings{pan-etal-2023-umuteam-semeval,
title = "{UMUT}eam at {S}em{E}val-2023 Task 3: Multilingual transformer-based model for detecting the Genre, the Framing, and the Persuasion Techniques in Online News",
author = "Pan, Ronghao and
Garc{\'\i}a-D{\'\i}az, Jos{\'e} Antonio and
{\'A}ngel Rodr{\'\i}guez-Garc{\'\i}a, Miguel and
Valencia-Garc{\'\i}a, Rafael",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.83",
doi = "10.18653/v1/2023.semeval-1.83",
pages = "609--615",
abstract = "In this manuscript, we describe the participation of the UMUTeam in SemEval-2023 Task 3, a shared task on detecting different aspects of news articles and other web documents, such as document category, framing dimensions, and persuasion technique in a multilingual setup. The task has been organized into three related subtasks, and we have been involved in the first two. Our approach is based on a fine-tuned multilingual transformer-based model that uses the dataset of all languages at once and a sentence transformer model to extract the most relevant chunk of a text for subtasks 1 and 2. The input data was truncated to 200 tokens with 50 overlaps using the sentence-transformer model to obtain the subset of text most related to the articles{'} titles. Our system has performed good results in subtask 1 in most languages, and in some cases, such as French and German, we have archived first place in the official leader board. As for task 2, our system has also performed very well in all languages, ranking in all the top 10.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2023-umuteam-semeval">
<titleInfo>
<title>UMUTeam at SemEval-2023 Task 3: Multilingual transformer-based model for detecting the Genre, the Framing, and the Persuasion Techniques in Online News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ronghao</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">García-Díaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ángel Rodríguez-García</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Valencia-García</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</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">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this manuscript, we describe the participation of the UMUTeam in SemEval-2023 Task 3, a shared task on detecting different aspects of news articles and other web documents, such as document category, framing dimensions, and persuasion technique in a multilingual setup. The task has been organized into three related subtasks, and we have been involved in the first two. Our approach is based on a fine-tuned multilingual transformer-based model that uses the dataset of all languages at once and a sentence transformer model to extract the most relevant chunk of a text for subtasks 1 and 2. The input data was truncated to 200 tokens with 50 overlaps using the sentence-transformer model to obtain the subset of text most related to the articles’ titles. Our system has performed good results in subtask 1 in most languages, and in some cases, such as French and German, we have archived first place in the official leader board. As for task 2, our system has also performed very well in all languages, ranking in all the top 10.</abstract>
<identifier type="citekey">pan-etal-2023-umuteam-semeval</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.83</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.83</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>609</start>
<end>615</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMUTeam at SemEval-2023 Task 3: Multilingual transformer-based model for detecting the Genre, the Framing, and the Persuasion Techniques in Online News
%A Pan, Ronghao
%A García-Díaz, José Antonio
%A Ángel Rodríguez-García, Miguel
%A Valencia-García, Rafael
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F pan-etal-2023-umuteam-semeval
%X In this manuscript, we describe the participation of the UMUTeam in SemEval-2023 Task 3, a shared task on detecting different aspects of news articles and other web documents, such as document category, framing dimensions, and persuasion technique in a multilingual setup. The task has been organized into three related subtasks, and we have been involved in the first two. Our approach is based on a fine-tuned multilingual transformer-based model that uses the dataset of all languages at once and a sentence transformer model to extract the most relevant chunk of a text for subtasks 1 and 2. The input data was truncated to 200 tokens with 50 overlaps using the sentence-transformer model to obtain the subset of text most related to the articles’ titles. Our system has performed good results in subtask 1 in most languages, and in some cases, such as French and German, we have archived first place in the official leader board. As for task 2, our system has also performed very well in all languages, ranking in all the top 10.
%R 10.18653/v1/2023.semeval-1.83
%U https://aclanthology.org/2023.semeval-1.83
%U https://doi.org/10.18653/v1/2023.semeval-1.83
%P 609-615
Markdown (Informal)
[UMUTeam at SemEval-2023 Task 3: Multilingual transformer-based model for detecting the Genre, the Framing, and the Persuasion Techniques in Online News](https://aclanthology.org/2023.semeval-1.83) (Pan et al., SemEval 2023)
ACL