@inproceedings{6f95c8c6e3d64ddcb083bc61337114f3,
title = "Analyzing Cognitive Plausibility of Subword Tokenization",
abstract = "Subword tokenization has become the de-facto standard for tokenization, although comparative evaluations of subword vocabulary 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 response time and accuracy of human performance on a lexical decision task. We compare three tokenization algorithms across several languages and vocabulary sizes. Our results indicate that the UnigramLM algorithm yields less cognitively plausible tokenization behavior and a worse coverage of derivational morphemes, in contrast with prior work.",
author = "Lisa Beinborn and Yuval Pinter",
note = "Publisher Copyright: {\textcopyright}2023 Association for Computational Linguistics.; 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 ; Conference date: 06-12-2023 Through 10-12-2023",
year = "2023",
month = jan,
day = "1",
doi = "10.18653/v1/2023.emnlp-main.272",
language = "American English",
series = "EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "4478--4486",
editor = "Houda Bouamor and Juan Pino and Kalika Bali",
booktitle = "EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings",
address = "United States",
}