English
Related papers

Related papers: A path to natural language through tokenisation an…

200 papers

Discovering causal direction from temporal observational data is particularly challenging for symbolic sequences, where functional models and noise assumptions are often unavailable. We propose a novel \emph{Dictionary Based Pattern Entropy…

Machine Learning · Statistics 2026-03-06 Harikrishnan N B , Shubham Bhilare , Aditi Kathpalia , Nithin Nagaraj

Analysing and modelling interactive behaviour is an important topic in human-computer interaction (HCI) and a key requirement for the development of intelligent interactive systems. Interactive behaviour has a sequential (actions happen one…

Human-Computer Interaction · Computer Science 2023-05-15 Guanhua Zhang , Matteo Bortoletto , Zhiming Hu , Lei Shi , Mihai Bâce , Andreas Bulling

Pre-tokenization, the initial step in many modern tokenization pipelines, segments text into smaller units called pretokens, typically splitting on whitespace and punctuation. While this process encourages having full, individual words as…

Computation and Language · Computer Science 2025-10-03 Craig W. Schmidt , Varshini Reddy , Chris Tanner , Yuval Pinter

In this article, we evaluate computational models of natural language with respect to the universal statistical behaviors of natural language. Statistical mechanical analyses have revealed that natural language text is characterized by…

Computation and Language · Computer Science 2019-06-25 Shuntaro Takahashi , Kumiko Tanaka-Ishii

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

Computation and Language · Computer Science 2024-06-04 Wenhong Zhu , Hongkun Hao , Zhiwei He , Yiming Ai , Rui Wang

Probabilistic language generators are theoretically modeled as discrete stochastic processes, yet standard decoding strategies (Top-k, Top-p) impose static truncation rules that fail to accommodate the dynamic information density of natural…

Computation and Language · Computer Science 2026-03-17 Deepon Halder , Raj Dabre

Recent dynamic tokenisation methods operate directly on bytes and pool their latent representations into patches. This bears similarities to computational models of word segmentation that determine lexical boundaries using spikes in an…

Computation and Language · Computer Science 2025-06-24 Zébulon Goriely , Suchir Salhan , Pietro Lesci , Julius Cheng , Paula Buttery

Scaling laws enable the optimal selection of data amount and language model size, yet the impact of the data unit, the token, on this relationship remains underexplored. In this work, we systematically investigate how the information…

Computation and Language · Computer Science 2026-05-27 Tomasz Limisiewicz , Artidoro Pagnoni , Srini Iyer , Mike Lewis , Sachin Mehta , Alisa Liu , Margaret Li , Gargi Ghosh , Luke Zettlemoyer

Modern language models represent probability distributions over character strings as distributions over (shorter) token strings derived via a deterministic tokenizer, such as byte-pair encoding. While this approach is highly effective at…

The emergence of telomere-to-telomere (T2T) genome assemblies has opened new avenues for comparative genomics, yet effective tokenization strategies for genomic sequences remain underexplored. In this pilot study, we apply Byte Pair…

Genomics · Quantitative Biology 2025-05-15 Marina Popova , Iaroslav Chelombitko , Aleksey Komissarov

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Words in natural language follow a Zipfian distribution whereby some words are frequent but most are rare. Learning representations for words in the "long tail" of this distribution requires enormous amounts of data. Representations of rare…

Machine Learning · Computer Science 2018-03-08 Dzmitry Bahdanau , Tom Bosc , Stanisław Jastrzębski , Edward Grefenstette , Pascal Vincent , Yoshua Bengio

We show how generalized Gibbs-Shannon entropies can provide new insights on the statistical properties of texts. The universal distribution of word frequencies (Zipf's law) implies that the generalized entropies, computed at the word level,…

Physics and Society · Physics 2017-02-15 Eduardo G. Altmann , Laercio Dias , Martin Gerlach

Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not…

Computation and Language · Computer Science 2023-10-20 Lihu Chen , Gaël Varoquaux , Fabian M. Suchanek

This paper studies the limits of language models' statistical learning in the context of Zipf's law. First, we demonstrate that Zipf-law token distribution emerges irrespective of the chosen tokenization. Second, we show that Zipf…

Computation and Language · Computer Science 2022-11-22 Elizaveta Zhemchuzhina , Nikolai Filippov , Ivan P. Yamshchikov

In this paper, we formalize practical byte pair encoding tokenization as it is used in large language models and other NLP systems, in particular we formally define and investigate the semantics of the SentencePiece and HuggingFace…

Formal Languages and Automata Theory · Computer Science 2023-09-19 Martin Berglund , Brink van der Merwe

By processing electronic health records (EHRs) as natural language sequences, large language models (LLMs) have shown potential in clinical prediction tasks such as mortality prediction and phenotyping. However, longitudinal or highly…

Computation and Language · Computer Science 2026-05-13 Mingcheng Zhu , Zhiyao Luo , Yu Liu , Tingting Zhu

Byte Pair Encoding (BPE) is a widely used tokenization algorithm, whose tokens cannot extend across pre-tokenization boundaries, functionally limiting it to representing at most full words. The BoundlessBPE and SuperBPE algorithms extend…

Computation and Language · Computer Science 2026-04-08 Craig W. Schmidt , Chris Tanner , Yuval Pinter

The success of pretrained transformer language models (LMs) in natural language processing has led to a wide range of pretraining setups. In particular, these models employ a variety of subword tokenization methods, most notably byte-pair…

Computation and Language · Computer Science 2020-10-06 Kaj Bostrom , Greg Durrett

What are the units of text that we want to model? From bytes to multi-word expressions, text can be analyzed and generated at many granularities. Until recently, most natural language processing (NLP) models operated over words, treating…