Nuclear and Atomic Physics

    

GlyphFormer: Improving Japanese Language Models with Sub-character Tokenization

Authors: Koichiro Kanno

This paper examines the effectiveness of using sub-character tokenization for Japanese language processing by utilizing the ALBERT [1] model. I focused on radical and element-based sub-character tokenization and compared the results with traditional character-based tokenization. The evaluation was conducted on a dataset derived from the Japanese novel "Botchan," containing 500 sentences. The results indicate that sub-character tokenization significantly improves the model's perplexity, especially when using radical and element-based approaches.

Comments: Pages.

Download: PDF

Submission history

[v1] 2024-08-19 18:42:20
[v2] 2024-09-15 20:43:20

Unique-IP document downloads: 496 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus