English
Related papers

Related papers: Tokenization and the Noiseless Channel

200 papers

The first step in any NLP pipeline is to split the text into individual tokens. The most obvious and straightforward approach is to use words as tokens. However, given a large text corpus, representing all the words is not efficient in…

Computation and Language · Computer Science 2021-09-30 Zaid Alyafeai , Maged S. Al-shaibani , Mustafa Ghaleb , Irfan Ahmad

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…

Computation and Language · Computer Science 2024-03-04 Jinbiao Yang

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Computation and Language · Computer Science 2025-11-14 Benjamin L. Badger , Matthew Neligeorge

Research in machine learning has questioned whether increases in training token counts reliably produce proportional performance gains in large language models. Building on prior work introducing an energy-aware parameter efficiency metric,…

Machine Learning · Computer Science 2026-01-13 Joe Dwyer

Tokenization is an understudied and often neglected component of modern LLMs. Most published works use a single tokenizer for all experiments, often borrowed from another model, without performing ablations or analysis to optimize…

Computation and Language · Computer Science 2024-02-08 Gautier Dagan , Gabriel Synnaeve , Baptiste Rozière

Traditionally, NLP performance improvement has been focused on improving models and increasing the number of model parameters. NLP vocabulary construction has remained focused on maximizing the number of words represented through subword…

Computation and Language · Computer Science 2023-04-26 Sandeep Mehta , Darpan Shah , Ravindra Kulkarni , Cornelia Caragea

Language models can largely benefit from efficient tokenization. However, they still mostly utilize the classical BPE algorithm, a simple and reliable method. This has been shown to cause such issues as under-trained tokens and sub-optimal…

Computation and Language · Computer Science 2024-09-10 Pavel Chizhov , Catherine Arnett , Elizaveta Korotkova , Ivan P. Yamshchikov

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…

Artificial Intelligence · Computer Science 2025-09-03 Andrew G. A. Correa , Ana C. H de Matos

The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues. Subword (SW) tokenization has been…

Computation and Language · Computer Science 2023-03-02 J. Pourmostafa Roshan Sharami , D. Shterionov , P. Spronck

This paper introduces an objective metric for evaluating a parsing scheme. It is based on Shannon's original work with letter sequences, which can be extended to part-of-speech tag sequences. It is shown that this regular language is an…

cmp-lg · Computer Science 2008-02-03 Caroline Lyon , Stephen Brown

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by…

Computation and Language · Computer Science 2022-03-16 Xiangyang Mou , Mo Yu , Bingsheng Yao , Lifu Huang

Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent tokenization approaches based on data-derived subword lexicons…

Computation and Language · Computer Science 2022-05-19 Jonathan H. Clark , Dan Garrette , Iulia Turc , John Wieting

Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training…

Computation and Language · Computer Science 2026-04-07 Yuchen Yang , Wenze Lin , Enhao Huang , Zhixuan Chu , Hongbin Zhou , Lan Tao , Yiming Li , Zhan Qin , Kui Ren

As one of the potential key technologies of 6G, semantic communication is still in its infancy and there are many open problems, such as semantic entropy definition and semantic channel coding theory. To address these challenges, we…

Information Theory · Computer Science 2025-02-20 Shuai Ma , Chuanhui Zhang , Huayan Qi , Hang Li , Yue Bi , Guangming Shi , Naofal Al-Dhahir

We study a quantity called discrete layered entropy, which approximates the Shannon entropy within a logarithmic gap. Compared to the Shannon entropy, the discrete layered entropy is piecewise linear, approximates the expected length of the…

Information Theory · Computer Science 2026-01-27 Cheuk Ting Li

Many of the traditional results in information theory, such as the channel coding theorem or the source coding theorem, are restricted to scenarios where the underlying resources are independent and identically distributed (i.i.d.) over a…

Quantum Physics · Physics 2009-06-28 Nilanjana Datta , Renato Renner

As an application of generalised statistical mechanics, it is studied a possible route toward a consistent generalised information theory in terms of a family of non-extensive, non-parametric entropies $H^\pm_D(P)$. Unlike other proposals…

Information Theory · Computer Science 2021-03-23 Jesús Fuentes , Octavio Obregón

Entropies must correspond to mean values for them to be measurable. The Shannon entropy corresponds to the weighted arithmetic mean, whereas the Renyi entropy corresponds to the exponential mean. These means refer to code lengths, which are…

Statistical Mechanics · Physics 2011-10-25 B. H. Lavenda