@inproceedings{pickard-do-2024-tuesents,
title = "{T}ue{S}ents at {S}em{E}val-2024 Task 8: Predicting the Shift from Human Authorship to Machine-generated Output in a Mixed Text",
author = "Pickard, Valentin and
Do, Hoa",
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-1.118",
doi = "10.18653/v1/2024.semeval-1.118",
pages = "829--832",
abstract = "This paper describes our approach and resultsfor the SemEval 2024 task of identifying thetoken index in a mixed text where a switchfrom human authorship to machine-generatedtext occurs. We explore two BiLSTMs, oneover sentence feature vectors to predict theindex of the sentence containing such a changeand another over character embeddings of thetext. As sentence features, we compute tokencount, mean token length, standard deviationof token length, counts for punctuation andspace characters, various readability scores,word frequency class and word part-of-speechclass counts for each sentence. class counts.The evaluation is performed on mean absoluteerror (MAE) between predicted and actualboundary token index. While our competitionresults were notably below the baseline, theremay still be useful aspects to our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pickard-do-2024-tuesents">
<titleInfo>
<title>TueSents at SemEval-2024 Task 8: Predicting the Shift from Human Authorship to Machine-generated Output in a Mixed Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Pickard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoa</namePart>
<namePart type="family">Do</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>This paper describes our approach and resultsfor the SemEval 2024 task of identifying thetoken index in a mixed text where a switchfrom human authorship to machine-generatedtext occurs. We explore two BiLSTMs, oneover sentence feature vectors to predict theindex of the sentence containing such a changeand another over character embeddings of thetext. As sentence features, we compute tokencount, mean token length, standard deviationof token length, counts for punctuation andspace characters, various readability scores,word frequency class and word part-of-speechclass counts for each sentence. class counts.The evaluation is performed on mean absoluteerror (MAE) between predicted and actualboundary token index. While our competitionresults were notably below the baseline, theremay still be useful aspects to our approach.</abstract>
<identifier type="citekey">pickard-do-2024-tuesents</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.118</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.118</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>829</start>
<end>832</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TueSents at SemEval-2024 Task 8: Predicting the Shift from Human Authorship to Machine-generated Output in a Mixed Text
%A Pickard, Valentin
%A Do, Hoa
%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 pickard-do-2024-tuesents
%X This paper describes our approach and resultsfor the SemEval 2024 task of identifying thetoken index in a mixed text where a switchfrom human authorship to machine-generatedtext occurs. We explore two BiLSTMs, oneover sentence feature vectors to predict theindex of the sentence containing such a changeand another over character embeddings of thetext. As sentence features, we compute tokencount, mean token length, standard deviationof token length, counts for punctuation andspace characters, various readability scores,word frequency class and word part-of-speechclass counts for each sentence. class counts.The evaluation is performed on mean absoluteerror (MAE) between predicted and actualboundary token index. While our competitionresults were notably below the baseline, theremay still be useful aspects to our approach.
%R 10.18653/v1/2024.semeval-1.118
%U https://aclanthology.org/2024.semeval-1.118
%U https://doi.org/10.18653/v1/2024.semeval-1.118
%P 829-832
Markdown (Informal)
[TueSents at SemEval-2024 Task 8: Predicting the Shift from Human Authorship to Machine-generated Output in a Mixed Text](https://aclanthology.org/2024.semeval-1.118) (Pickard & Do, SemEval 2024)
ACL