# Vaporetto: Efficient Japanese Tokenization Based on Improved Pointwise Linear Classification

arXiv: https://arxiv.org/abs/2406.17185 · HTML: https://mlsanity.com/paper/2406.17185/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 27 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 3 of 3)

- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Fast WordPiece Tokenization](https://mlsanity.com/paper/2012.15524/) (2020)
- [Long Short-Term Memory for Japanese Word Segmentation](https://mlsanity.com/paper/1709.08011/) (2017)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study](https://mlsanity.com/paper/2606.22009/) (2026)

## Abstract (arXiv)

This paper proposes an approach to improve the runtime efficiency of Japanese tokenization based on the pointwise linear classification (PLC) framework, which formulates the whole tokenization process as a sequence of linear classification problems. Our approach optimizes tokenization by leveraging the characteristics of the PLC framework and the task definition. Our approach involves (1) composing multiple classifications into array-based operations, (2) efficient feature lookup with memory-optimized automata, and (3) three orthogonal pre-processing methods for reducing actual score calculation. Thus, our approach makes the tokenization speed 5.7 times faster than the current approach based on the same model without decreasing tokenization accuracy. Our implementation is available at https://github.com/daac-tools/vaporetto under the MIT or Apache-2.0 license.