@inproceedings{alecakir-etal-2024-groningen,
title = "{G}roningen Team A at {S}em{E}val-2024 Task 8: Human/Machine Authorship Attribution Using a Combination of Probabilistic and Linguistic Features",
author = "Alecakir, Huseyin and
Chakraborty, Puja and
Henningsson, Pontus and
Van Hofslot, Matthijs and
Scheuer, Alon",
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-1.269",
doi = "10.18653/v1/2024.semeval-1.269",
pages = "1926--1932",
abstract = "Our approach primarily centers on feature-based systems, where a diverse array of features pertinent to the text{'}s linguistic attributes is extracted. Alongside those, we incorporate token-level probabilistic features which are fed into a Bidirectional Long Short-Term Memory (BiLSTM) model. Both resulting feature arrays are concatenated and fed into our final prediction model. Our method under-performed compared to the baseline, despite the fact that previous attempts by others have successfully used linguistic features for the purpose of discerning machine-generated text. We conclude that our examined subset of linguistically motivated features alongside probabilistic features was not able to contribute almost any performance at all to a hybrid classifier of human and machine texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alecakir-etal-2024-groningen">
<titleInfo>
<title>Groningen Team A at SemEval-2024 Task 8: Human/Machine Authorship Attribution Using a Combination of Probabilistic and Linguistic Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huseyin</namePart>
<namePart type="family">Alecakir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Puja</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pontus</namePart>
<namePart type="family">Henningsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthijs</namePart>
<namePart type="family">Van Hofslot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Scheuer</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>Our approach primarily centers on feature-based systems, where a diverse array of features pertinent to the text’s linguistic attributes is extracted. Alongside those, we incorporate token-level probabilistic features which are fed into a Bidirectional Long Short-Term Memory (BiLSTM) model. Both resulting feature arrays are concatenated and fed into our final prediction model. Our method under-performed compared to the baseline, despite the fact that previous attempts by others have successfully used linguistic features for the purpose of discerning machine-generated text. We conclude that our examined subset of linguistically motivated features alongside probabilistic features was not able to contribute almost any performance at all to a hybrid classifier of human and machine texts.</abstract>
<identifier type="citekey">alecakir-etal-2024-groningen</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.269</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.269</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1926</start>
<end>1932</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Groningen Team A at SemEval-2024 Task 8: Human/Machine Authorship Attribution Using a Combination of Probabilistic and Linguistic Features
%A Alecakir, Huseyin
%A Chakraborty, Puja
%A Henningsson, Pontus
%A Van Hofslot, Matthijs
%A Scheuer, Alon
%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 alecakir-etal-2024-groningen
%X Our approach primarily centers on feature-based systems, where a diverse array of features pertinent to the text’s linguistic attributes is extracted. Alongside those, we incorporate token-level probabilistic features which are fed into a Bidirectional Long Short-Term Memory (BiLSTM) model. Both resulting feature arrays are concatenated and fed into our final prediction model. Our method under-performed compared to the baseline, despite the fact that previous attempts by others have successfully used linguistic features for the purpose of discerning machine-generated text. We conclude that our examined subset of linguistically motivated features alongside probabilistic features was not able to contribute almost any performance at all to a hybrid classifier of human and machine texts.
%R 10.18653/v1/2024.semeval-1.269
%U https://aclanthology.org/2024.semeval-1.269
%U https://doi.org/10.18653/v1/2024.semeval-1.269
%P 1926-1932
Markdown (Informal)
[Groningen Team A at SemEval-2024 Task 8: Human/Machine Authorship Attribution Using a Combination of Probabilistic and Linguistic Features](https://aclanthology.org/2024.semeval-1.269) (Alecakir et al., SemEval 2024)
ACL