@inproceedings{lepekhin-sharoff-2023-ftd,
title = "{FTD} at {S}em{E}val-2023 Task 3: News Genre and Propaganda Detection by Comparing Mono- and Multilingual Models with Fine-tuning on Additional Data",
author = "Lepekhin, Mikhail and
Sharoff, Serge",
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-1.76/",
doi = "10.18653/v1/2023.semeval-1.76",
pages = "549--555",
abstract = "We report our participation in the SemEval-2023 shared task on propaganda detection and describe our solutions with pre-trained models and their ensembles. For Subtask 1 (News Genre Categorisation), we report the impact of several settings, such as the choice of the classification models (monolingual or multilingual or their ensembles), the choice of the training sets (base or additional sources), the impact of detection certainty in making a classification decision as well as the impact of other hyper-parameters. In particular, we fine-tune models on additional data for other genre classification tasks, such as FTD. We also try adding texts from genre-homogenous corpora, such as Panorama, Babylon Bee for satire and Giganews for for reporting texts. We also make prepared models for Subtasks 2 and 3 with finetuning the corresponding models first for Subtask 1.The code needed to reproduce the experiments is available."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lepekhin-sharoff-2023-ftd">
<titleInfo>
<title>FTD at SemEval-2023 Task 3: News Genre and Propaganda Detection by Comparing Mono- and Multilingual Models with Fine-tuning on Additional Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Lepekhin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</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>We report our participation in the SemEval-2023 shared task on propaganda detection and describe our solutions with pre-trained models and their ensembles. For Subtask 1 (News Genre Categorisation), we report the impact of several settings, such as the choice of the classification models (monolingual or multilingual or their ensembles), the choice of the training sets (base or additional sources), the impact of detection certainty in making a classification decision as well as the impact of other hyper-parameters. In particular, we fine-tune models on additional data for other genre classification tasks, such as FTD. We also try adding texts from genre-homogenous corpora, such as Panorama, Babylon Bee for satire and Giganews for for reporting texts. We also make prepared models for Subtasks 2 and 3 with finetuning the corresponding models first for Subtask 1.The code needed to reproduce the experiments is available.</abstract>
<identifier type="citekey">lepekhin-sharoff-2023-ftd</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.76</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.76/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>549</start>
<end>555</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FTD at SemEval-2023 Task 3: News Genre and Propaganda Detection by Comparing Mono- and Multilingual Models with Fine-tuning on Additional Data
%A Lepekhin, Mikhail
%A Sharoff, Serge
%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 lepekhin-sharoff-2023-ftd
%X We report our participation in the SemEval-2023 shared task on propaganda detection and describe our solutions with pre-trained models and their ensembles. For Subtask 1 (News Genre Categorisation), we report the impact of several settings, such as the choice of the classification models (monolingual or multilingual or their ensembles), the choice of the training sets (base or additional sources), the impact of detection certainty in making a classification decision as well as the impact of other hyper-parameters. In particular, we fine-tune models on additional data for other genre classification tasks, such as FTD. We also try adding texts from genre-homogenous corpora, such as Panorama, Babylon Bee for satire and Giganews for for reporting texts. We also make prepared models for Subtasks 2 and 3 with finetuning the corresponding models first for Subtask 1.The code needed to reproduce the experiments is available.
%R 10.18653/v1/2023.semeval-1.76
%U https://aclanthology.org/2023.semeval-1.76/
%U https://doi.org/10.18653/v1/2023.semeval-1.76
%P 549-555
Markdown (Informal)
[FTD at SemEval-2023 Task 3: News Genre and Propaganda Detection by Comparing Mono- and Multilingual Models with Fine-tuning on Additional Data](https://aclanthology.org/2023.semeval-1.76/) (Lepekhin & Sharoff, SemEval 2023)
ACL