@inproceedings{devatine-etal-2023-melodi,
title = "{MELODI} at {S}em{E}val-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles",
author = "Devatine, Nicolas and
Muller, Philippe and
Braud, Chlo{\'e}",
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-1.14",
doi = "10.18653/v1/2023.semeval-1.14",
pages = "108--113",
abstract = "This paper describes our approach to Subtask 1 {``}News Genre Categorization{''} of SemEval-2023 Task 3 {``}Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup{''}, which aims to determine whether a given news article is an opinion piece, an objective report, or satirical. We fine-tuned the domain-specific language model POLITICS, which was pre-trained on a large-scale dataset of more than 3.6M English political news articles following ideology-driven pre-training objectives. In order to use it in the multilingual setup of the task, we added as a pre-processing step the translation of all documents into English. Our system ranked among the top systems overall in most language, and ranked 1st on the English dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devatine-etal-2023-melodi">
<titleInfo>
<title>MELODI at SemEval-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Devatine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</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>This paper describes our approach to Subtask 1 “News Genre Categorization” of SemEval-2023 Task 3 “Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup”, which aims to determine whether a given news article is an opinion piece, an objective report, or satirical. We fine-tuned the domain-specific language model POLITICS, which was pre-trained on a large-scale dataset of more than 3.6M English political news articles following ideology-driven pre-training objectives. In order to use it in the multilingual setup of the task, we added as a pre-processing step the translation of all documents into English. Our system ranked among the top systems overall in most language, and ranked 1st on the English dataset.</abstract>
<identifier type="citekey">devatine-etal-2023-melodi</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.14</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>108</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MELODI at SemEval-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles
%A Devatine, Nicolas
%A Muller, Philippe
%A Braud, Chloé
%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 devatine-etal-2023-melodi
%X This paper describes our approach to Subtask 1 “News Genre Categorization” of SemEval-2023 Task 3 “Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup”, which aims to determine whether a given news article is an opinion piece, an objective report, or satirical. We fine-tuned the domain-specific language model POLITICS, which was pre-trained on a large-scale dataset of more than 3.6M English political news articles following ideology-driven pre-training objectives. In order to use it in the multilingual setup of the task, we added as a pre-processing step the translation of all documents into English. Our system ranked among the top systems overall in most language, and ranked 1st on the English dataset.
%R 10.18653/v1/2023.semeval-1.14
%U https://aclanthology.org/2023.semeval-1.14
%U https://doi.org/10.18653/v1/2023.semeval-1.14
%P 108-113
Markdown (Informal)
[MELODI at SemEval-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles](https://aclanthology.org/2023.semeval-1.14) (Devatine et al., SemEval 2023)
ACL