English
Related papers

Related papers: Tokenization and the Noiseless Channel

200 papers

Estimation of Shannon and R\'enyi entropies of unknown discrete distributions is a fundamental problem in statistical property testing and an active research topic in both theoretical computer science and information theory. Tight bounds on…

Quantum Physics · Physics 2023-07-19 Tongyang Li , Xiaodi Wu

Tokenization is a fundamental step in natural language processing (NLP) and other sequence modeling domains, where the choice of vocabulary size significantly impacts model performance. Despite its importance, selecting an optimal…

Machine Learning · Computer Science 2025-07-31 Yanjin He , Qingkai Zeng , Meng Jiang

Shannon entropy is the shortest average codeword length a lossless compressor can achieve by encoding i.i.d. symbols. However, there are cases in which the objective is to minimize the \textit{exponential} average codeword length, i.e. when…

Information Theory · Computer Science 2024-06-10 Andrea Somazzi , Paolo Ferragina , Diego Garlaschelli

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Computation and Language · Computer Science 2025-08-22 Dong Liu , Yanxuan Yu

Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training. BPE and MaxMatch, two…

Computation and Language · Computer Science 2024-08-22 Marco Cognetta , Vilém Zouhar , Naoaki Okazaki

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

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

Transformers are strong baselines in both vision and language because self-attention captures long-range dependencies across tokens. However, the cost of self-attention grows quadratically with the number of tokens. Patch pruning mitigates…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Hiroaki Aizawa , Yuki Igaue

It is known that given the real sum of two independent uniformly distributed lattice points from the same nested lattice codebook, the eavesdropper can obtain at most 1 bit of information per channel regarding the value of one of the…

Information Theory · Computer Science 2009-10-15 Xiang He , Aylin Yener

From the output produced by a memoryless deletion channel from a uniformly random input of known length $n$, one obtains a posterior distribution on the channel input. The difference between the Shannon entropy of this distribution and that…

Information Theory · Computer Science 2018-08-01 Arash Atashpendar , David Mestel , A. W. Roscoe , Peter Y. A. Ryan

Properties of scalar quantization with $r$th power distortion and constrained R\'enyi entropy of order $\alpha\in (0,1)$ are investigated. For an asymptotically (high-rate) optimal sequence of quantizers, the contribution to the R\'enyi…

Information Theory · Computer Science 2012-03-27 Wolfgang Kreitmeier , Tamas Linder

The choice of tokenizer can profoundly impact language model performance, yet accessible and reliable evaluations of tokenizer quality remain an open challenge. Inspired by scaling consistency, we show that smaller models can accurately…

Computation and Language · Computer Science 2025-06-04 Jonas F. Lotz , António V. Lopes , Stephan Peitz , Hendra Setiawan , Leonardo Emili

Tokenization is fundamental in assembly code analysis, impacting intrinsic characteristics like vocabulary size, semantic coverage, and extrinsic performance in downstream tasks. Despite its significance, tokenization in the context of…

Artificial Intelligence · Computer Science 2025-11-07 Ahmed Mostafa , Raisul Arefin Nahid , Samuel Mulder

Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor languages dominant in the training data and consequently…

Computation and Language · Computer Science 2025-08-25 Negar Foroutan , Clara Meister , Debjit Paul , Joel Niklaus , Sina Ahmadi , Antoine Bosselut , Rico Sennrich

A central question in information theory is to determine the maximum success probability that can be achieved in sending a fixed number of messages over a noisy channel. This was first studied in the pioneering work of Shannon who…

Information Theory · Computer Science 2018-06-25 Siddharth Barman , Omar Fawzi

The matrix-based R\'enyi's entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it widely applied in statistical…

Machine Learning · Computer Science 2022-12-01 Yuxin Dong , Tieliang Gong , Shujian Yu , Hong Chen , Chen Li

This paper provides tight bounds on the R\'enyi entropy of a function of a discrete random variable with a finite number of possible values, where the considered function is not one-to-one. To that end, a tight lower bound on the R\'enyi…

Information Theory · Computer Science 2018-12-11 Igal Sason

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

Computation and Language · Computer Science 2025-04-15 Buu Phan , Brandon Amos , Itai Gat , Marton Havasi , Matthew Muckley , Karen Ullrich

Feature selection, in the context of machine learning, is the process of separating the highly predictive feature from those that might be irrelevant or redundant. Information theory has been recognized as a useful concept for this task, as…

Machine Learning · Computer Science 2020-01-28 Catuscia Palamidessi , Marco Romanelli

Information theory is introduced in this lecture note with a particular emphasis on its relevance to algebraic coding theory. The document develops the mathematical foundations for quantifying uncertainty and information transmission by…

Information Theory · Computer Science 2025-12-08 El Mahdi Mouloua , Essaid Mohamed