English
Related papers

Related papers: Which Pieces Does Unigram Tokenization Really Need…

200 papers

Tokenization is a critical preprocessing step for large language models (LLMs), directly impacting training efficiency and downstream performance. General-purpose tokenizers trained predominantly on English and Latin-script languages…

Computation and Language · Computer Science 2025-12-23 Mark Kashirskiy , Artiom Lipinski , Ilya Makarov

Byte-Pair Encoding (BPE) has become a widely adopted subword tokenization method in modern language models due to its simplicity and strong empirical performance across downstream tasks. However, applying BPE to unsegmented languages such…

Computation and Language · Computer Science 2025-06-23 Yifan Hu , Frank Liang , Dachuan Zhao , Jonathan Geuter , Varshini Reddy , Craig W. Schmidt , Chris Tanner

This paper addresses the problem of correcting spelling errors that result in valid, though unintended words (such as ``peace'' and ``piece'', or ``quiet'' and ``quite'') and also the problem of correcting particular word usage errors (such…

cmp-lg · Computer Science 2008-02-03 Andrew R. Golding , Yves Schabes

Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by breaking down words…

Computation and Language · Computer Science 2025-05-23 Sudhansu Bala Das , Samujjal Choudhury , Tapas Kumar Mishra , Bidyut Kr. Patra

Subword tokenization methods, such as Byte-Pair Encoding (BPE), significantly impact the performance and efficiency of large language models (LLMs). The standard approach involves training a general-purpose tokenizer that uniformly…

Computation and Language · Computer Science 2026-01-30 Vijini Liyanage , François Yvon

We propose a method to improve traditional character-based PPM text compression algorithms. Consider a text file as a sequence of alternating words and non-words, the basic idea of our algorithm is to encode non-words and prefixes of words…

Information Theory · Computer Science 2015-03-17 Yichuan Hu , Jianzhong , Zhang , Farooq Khan , Ying Li

Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make locally optimal decisions without considering the resulting vocabulary as a whole. We…

Computation and Language · Computer Science 2026-05-22 Jan Tempus , Philip Whittington , Craig W. Schmidt , Dennis Komm , Tiago Pimentel

Mixtures of Unigrams are one of the simplest and most efficient tools for clustering textual data, as they assume that documents related to the same topic have similar distributions of terms, naturally described by Multinomials. When the…

Machine Learning · Statistics 2020-12-10 Cinzia Viroli , Laura Anderlucci

Our work is motivated by the challenges presented in preparing arrays of atoms for use in quantum simulation. The recently-developed process of loading atoms into traps results in approximately half of the traps being filled. To consolidate…

Computational Complexity · Computer Science 2025-04-09 Alexandre Cooper , Stephanie Maaz , Amer E. Mouawad , Naomi Nishimura

Traditional greedy tokenization methods have been a critical step in Natural Language Processing (NLP), influencing how text is converted into tokens and directly impacting model performance. While subword tokenizers like Byte-Pair Encoding…

Computation and Language · Computer Science 2025-05-05 Bharath Raj , Garvit Suri , Vikrant Dewangan , Raghav Sonavane

The method of random projections has become very popular for large-scale applications in statistical learning, information retrieval, bio-informatics and other applications. Using a well-designed coding scheme for the projected data, which…

Machine Learning · Computer Science 2013-08-12 Ping Li , Michael Mitzenmacher , Anshumali Shrivastava

Algorithms with unitary oracles can be nested, which makes them extremely versatile. An example is the phase estimation algorithm used in many candidate algorithms for quantum speed-up. The search for new quantum algorithms benefits from…

Quantum Physics · Physics 2024-04-01 Zuzana Gavorová , Matan Seidel , Yonathan Touati

Quantum algorithms require a universal set of gates that can be implemented in a physical system. For these, an optimal decomposition into a sequence of available operations is desired. Here, we present a method to find such sequences for a…

Quantum Physics · Physics 2016-07-22 Esteban A. Martinez , Thomas Monz , Daniel Nigg , Philipp Schindler , Rainer Blatt

Tokenization is the first step in modern neural language model pipelines where an input text is converted to a sequence of subword tokens. We introduce from first principles a finite-state transduction framework which can efficiently encode…

Computation and Language · Computer Science 2024-10-22 Marco Cognetta , Naoaki Okazaki

This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case study. The tokenizer…

Computation and Language · Computer Science 2023-06-19 Takuro Fujii , Koki Shibata , Atsuki Yamaguchi , Terufumi Morishita , Yasuhiro Sogawa

Byte Pair Encoding (BPE) tokenizers, widely used in Large Language Models, face challenges in multilingual settings, including penalization of non-Western scripts and the creation of tokens with partial UTF-8 sequences. Pretokenization,…

Computation and Language · Computer Science 2025-06-02 Sander Land , Catherine Arnett

Partition of unity methods (PUMs) on graphs are simple and highly adaptive auxiliary tools for graph signal processing. Based on a greedy-type metric clustering and augmentation scheme, we show how a partition of unity can be generated in…

Signal Processing · Electrical Eng. & Systems 2020-12-22 Roberto Cavoretto , Alessandra De Rossi , Wolfgang Erb

The method is introduced for fast data processing by reducing the probability amplitudes of undesirable elements. The algorithm has a mathematical description and circuit implementation on a quantum processor. The idea is to make a quick…

Quantum Physics · Physics 2025-04-24 Karina Zakharova , Artem Chernikov , Sergey Sysoev

This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python implementations for subword…

Computation and Language · Computer Science 2018-08-21 Taku Kudo , John Richardson

We present a quantum algorithm for European option pricing in finance, where the key idea is to work in the unary representation of the asset value. The algorithm needs novel circuitry and is divided in three parts: first, the amplitude…