@inproceedings{beinborn-pinter-2023-analyzing,
    title = "Analyzing Cognitive Plausibility of Subword Tokenization",
    author = "Beinborn, Lisa  and
      Pinter, Yuval",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.emnlp-main.272/",
    doi = "10.18653/v1/2023.emnlp-main.272",
    pages = "4478--4486",
    abstract = "Subword tokenization has become the de-facto standard for tokenization although comparative evaluations of their quality across languages are scarce. Existing evaluation studies focus on the effect of a tokenization algorithm on the performance in downstream tasks, or on engineering criteria such as the compression rate. We present a new evaluation paradigm that focuses on the cognitive plausibility of subword tokenization. We analyze the correlation of the tokenizer output with the reading time and accuracy of human responses on a lexical decision task. We compare three tokenization algorithms across several languages and vocabulary sizes. Our results indicate that the Unigram algorithm yields less cognitively plausible tokenization behavior and a worse coverage of derivational morphemes, in contrast with prior work."
}