@inproceedings{keinan-2024-text,
    title = "Text Mining at {S}em{E}val-2024 Task 1: Evaluating Semantic Textual Relatedness in Low-resource Languages using Various Embedding Methods and Machine Learning Regression Models",
    author = "Keinan, Ron",
    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-1.65/",
    doi = "10.18653/v1/2024.semeval-1.65",
    pages = "420--431",
    abstract = "In this paper, I describe my submission to the SemEval-2024 contest. I tackled subtask 1 - {\textquotedblleft}Semantic Textual Relatedness for African and Asian Languages{\textquotedblright}. To find the semantic relatedness of sentence pairs, I tackled this task by creating models for nine different languages. I then vectorized the text data using a variety of embedding techniques including doc2vec, tf-idf, Sentence-Transformers, Bert, Roberta, and more, and used 11 traditional machine learning techniques of the regression type for analysis and evaluation."
}