@inproceedings{ben-fares-etal-2024-fi,
title = "{FI} Group at {S}em{E}val-2024 Task 8: A Syntactically Motivated Architecture for Multilingual Machine-Generated Text Detection",
author = "Ben-fares, Maha and
Zaratiana, Urchade and
Hernandez, Simon and
Holat, Pierre",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.170/",
doi = "10.18653/v1/2024.semeval-1.170",
pages = "1166--1171",
abstract = "In this paper, we present the description of our proposed system for Subtask A - multilingual track at SemEval-2024 Task 8, which aims to classify if text has been generated by an AI or Human. Our approach treats binary text classification as token-level prediction, with the final classification being the average of token-level predictions. Through the use of rich representations of pre-trained transformers, our model is trained to selectively aggregate information from across different layers to score individual tokens, given that each layer may contain distinct information. Notably, our model demonstrates competitive performance on the test dataset, achieving an accuracy score of 95.8{\%}. Furthermore, it secures the 2nd position in the multilingual track of Subtask A, with a mere 0.1{\%} behind the leading system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ben-fares-etal-2024-fi">
<titleInfo>
<title>FI Group at SemEval-2024 Task 8: A Syntactically Motivated Architecture for Multilingual Machine-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maha</namePart>
<namePart type="family">Ben-fares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Urchade</namePart>
<namePart type="family">Zaratiana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Holat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</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">Harish</namePart>
<namePart type="family">Tayyar Madabushi</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">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the description of our proposed system for Subtask A - multilingual track at SemEval-2024 Task 8, which aims to classify if text has been generated by an AI or Human. Our approach treats binary text classification as token-level prediction, with the final classification being the average of token-level predictions. Through the use of rich representations of pre-trained transformers, our model is trained to selectively aggregate information from across different layers to score individual tokens, given that each layer may contain distinct information. Notably, our model demonstrates competitive performance on the test dataset, achieving an accuracy score of 95.8%. Furthermore, it secures the 2nd position in the multilingual track of Subtask A, with a mere 0.1% behind the leading system.</abstract>
<identifier type="citekey">ben-fares-etal-2024-fi</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.170</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.170/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1166</start>
<end>1171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FI Group at SemEval-2024 Task 8: A Syntactically Motivated Architecture for Multilingual Machine-Generated Text Detection
%A Ben-fares, Maha
%A Zaratiana, Urchade
%A Hernandez, Simon
%A Holat, Pierre
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F ben-fares-etal-2024-fi
%X In this paper, we present the description of our proposed system for Subtask A - multilingual track at SemEval-2024 Task 8, which aims to classify if text has been generated by an AI or Human. Our approach treats binary text classification as token-level prediction, with the final classification being the average of token-level predictions. Through the use of rich representations of pre-trained transformers, our model is trained to selectively aggregate information from across different layers to score individual tokens, given that each layer may contain distinct information. Notably, our model demonstrates competitive performance on the test dataset, achieving an accuracy score of 95.8%. Furthermore, it secures the 2nd position in the multilingual track of Subtask A, with a mere 0.1% behind the leading system.
%R 10.18653/v1/2024.semeval-1.170
%U https://aclanthology.org/2024.semeval-1.170/
%U https://doi.org/10.18653/v1/2024.semeval-1.170
%P 1166-1171
Markdown (Informal)
[FI Group at SemEval-2024 Task 8: A Syntactically Motivated Architecture for Multilingual Machine-Generated Text Detection](https://aclanthology.org/2024.semeval-1.170/) (Ben-fares et al., SemEval 2024)
ACL