@inproceedings{041dc8be9d4247b395b43d8b3930213f,
title = "Turkish Delights: a Dataset on Turkish Euphemisms",
abstract = "Euphemisms are a form of figurative language relatively understudied in natural language processing. This research extends the current computational work on potentially euphemistic terms (PETs) to Turkish. We introduce the Turkish PET dataset, the first available of its kind in the field. By creating a list of euphemisms in Turkish, collecting example contexts, and annotating them, we provide both euphemistic and non-euphemistic examples of PETs in Turkish. We describe the dataset and methodologies, and also experiment with transformer-based models on Turkish euphemism detection by using our dataset for binary classification. We compare performances across models using F1, accuracy, and precision as evaluation metrics.",
author = "Biyik, {Hasan Can} and Patrick Lee and Anna Feldman",
note = "Publisher Copyright: {\textcopyright}2024 Association for Computational Linguistics.; 1st Workshop on Natural Language Processing for Turkic Languages, SIGTURK 2024 ; Conference date: 15-08-2024",
year = "2024",
language = "English",
series = "SIGTURK 2024 - 1st Workshop on Natural Language Processing for Turkic Languages, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "71--80",
editor = "Duygu Ataman and Derin, {Mehmet Oguz} and Sardana Ivanova and Abdullatif Koksal and Jonne Saleva and Deniz Zeyrek",
booktitle = "SIGTURK 2024 - 1st Workshop on Natural Language Processing for Turkic Languages, Proceedings of the Workshop",
address = "United States",
}