@inproceedings{pulipaka-etal-2024-semeval,
title = "{S}em{E}val Task 8: A Comparison of Traditional and Neural Models for Detecting Machine Authored Text",
author = {Pulipaka, Srikar Kashyap and
Mhalgi, Shrirang and
Larson, Joseph and
K{\"u}bler, Sandra},
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-1.148",
doi = "10.18653/v1/2024.semeval-1.148",
pages = "1026--1031",
abstract = {Since Large Language Models have reached a stage where it is becoming more and more difficult to distinguish between human and machine written text, there is an increasing need for automated systems to distinguish between them. As part of SemEval Task 8, Subtask A: Binary Human-Written vs. Machine-Generated Text Classification, we explore a variety of machine learning classifiers, from traditional statistical methods, such as Na{\"\i}ve Bayes and Decision Trees, to fine-tuned transformer models, suchas RoBERTa and ALBERT. Our findings show that using a fine-tuned RoBERTa model with optimizedhyperparameters yields the best accuracy. However, the improvement does not translate to the test set because of the differences in distribution in the development and test sets.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pulipaka-etal-2024-semeval">
<titleInfo>
<title>SemEval Task 8: A Comparison of Traditional and Neural Models for Detecting Machine Authored Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srikar</namePart>
<namePart type="given">Kashyap</namePart>
<namePart type="family">Pulipaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrirang</namePart>
<namePart type="family">Mhalgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Larson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</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>Since Large Language Models have reached a stage where it is becoming more and more difficult to distinguish between human and machine written text, there is an increasing need for automated systems to distinguish between them. As part of SemEval Task 8, Subtask A: Binary Human-Written vs. Machine-Generated Text Classification, we explore a variety of machine learning classifiers, from traditional statistical methods, such as Naïve Bayes and Decision Trees, to fine-tuned transformer models, suchas RoBERTa and ALBERT. Our findings show that using a fine-tuned RoBERTa model with optimizedhyperparameters yields the best accuracy. However, the improvement does not translate to the test set because of the differences in distribution in the development and test sets.</abstract>
<identifier type="citekey">pulipaka-etal-2024-semeval</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.148</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.148</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1026</start>
<end>1031</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemEval Task 8: A Comparison of Traditional and Neural Models for Detecting Machine Authored Text
%A Pulipaka, Srikar Kashyap
%A Mhalgi, Shrirang
%A Larson, Joseph
%A Kübler, Sandra
%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 pulipaka-etal-2024-semeval
%X Since Large Language Models have reached a stage where it is becoming more and more difficult to distinguish between human and machine written text, there is an increasing need for automated systems to distinguish between them. As part of SemEval Task 8, Subtask A: Binary Human-Written vs. Machine-Generated Text Classification, we explore a variety of machine learning classifiers, from traditional statistical methods, such as Naïve Bayes and Decision Trees, to fine-tuned transformer models, suchas RoBERTa and ALBERT. Our findings show that using a fine-tuned RoBERTa model with optimizedhyperparameters yields the best accuracy. However, the improvement does not translate to the test set because of the differences in distribution in the development and test sets.
%R 10.18653/v1/2024.semeval-1.148
%U https://aclanthology.org/2024.semeval-1.148
%U https://doi.org/10.18653/v1/2024.semeval-1.148
%P 1026-1031
Markdown (Informal)
[SemEval Task 8: A Comparison of Traditional and Neural Models for Detecting Machine Authored Text](https://aclanthology.org/2024.semeval-1.148) (Pulipaka et al., SemEval 2024)
ACL