@inproceedings{tran-tran-2024-newbieml,
title = "{N}ewbie{ML} at {S}em{E}val-2024 Task 8: Ensemble Approach for Multidomain Machine-Generated Text Detection",
author = "Tran, Bao and
Tran, Nhi",
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-1.54",
pages = "354--360",
abstract = "Large Language Models (LLMs) are becoming popular and easily accessible, leading to a large growth of machine-generated content over various channels. Along with this popularity, the potential misuse is also a challenge for us. In this paper, we use SemEval 2024 task A monolingual dataset with comparative study between some machine learning model with feature extraction and develop an ensemble method for our system. Our system achieved 84.31{\%} accuracy score in the test set, ranked 36th of 137 participants. Our code is available at: https://github.com/baoivy/SemEval-Task8",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-tran-2024-newbieml">
<titleInfo>
<title>NewbieML at SemEval-2024 Task 8: Ensemble Approach for Multidomain Machine-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bao</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nhi</namePart>
<namePart type="family">Tran</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>Large Language Models (LLMs) are becoming popular and easily accessible, leading to a large growth of machine-generated content over various channels. Along with this popularity, the potential misuse is also a challenge for us. In this paper, we use SemEval 2024 task A monolingual dataset with comparative study between some machine learning model with feature extraction and develop an ensemble method for our system. Our system achieved 84.31% accuracy score in the test set, ranked 36th of 137 participants. Our code is available at: https://github.com/baoivy/SemEval-Task8</abstract>
<identifier type="citekey">tran-tran-2024-newbieml</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.54</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>354</start>
<end>360</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NewbieML at SemEval-2024 Task 8: Ensemble Approach for Multidomain Machine-Generated Text Detection
%A Tran, Bao
%A Tran, Nhi
%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 tran-tran-2024-newbieml
%X Large Language Models (LLMs) are becoming popular and easily accessible, leading to a large growth of machine-generated content over various channels. Along with this popularity, the potential misuse is also a challenge for us. In this paper, we use SemEval 2024 task A monolingual dataset with comparative study between some machine learning model with feature extraction and develop an ensemble method for our system. Our system achieved 84.31% accuracy score in the test set, ranked 36th of 137 participants. Our code is available at: https://github.com/baoivy/SemEval-Task8
%U https://aclanthology.org/2024.semeval-1.54
%P 354-360
Markdown (Informal)
[NewbieML at SemEval-2024 Task 8: Ensemble Approach for Multidomain Machine-Generated Text Detection](https://aclanthology.org/2024.semeval-1.54) (Tran & Tran, SemEval 2024)
ACL