@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://preview.aclanthology.org/jlcl-multiple-ingestion/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."
}