English
Related papers

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

200 papers

A family of information theoretic models of communication was introduced more than a decade ago to explain the origins of Zipf's law for word frequencies. The family is a based on a combination of two information theoretic principles:…

Physics and Society · Physics 2020-09-24 Ramon Ferrer-i-Cancho

We study a deliberately simple, fully non-linguistic model of text: a sequence of independent draws from a finite alphabet of letters plus a single space symbol. A word is defined as a maximal block of non-space symbols. Within this…

Computation and Language · Computer Science 2025-11-25 Vladimir Berman

Human language has a distinct systematic structure, where utterances break into individually meaningful words which are combined to form phrases. We show that natural-language-like systematicity arises in codes that are constrained by a…

Computation and Language · Computer Science 2025-11-19 Richard Futrell , Michael Hahn

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…

Machine Learning · Computer Science 2026-02-13 Hakaze Cho , Haolin Yang , Yanshu Li , Brian M. Kurkoski , Naoya Inoue

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in…

Computation and Language · Computer Science 2026-03-05 Chunyuan Deng , Sanket Lokegaonkar , Colin Lockard , Besnik Fetahu , Nasser Zalmout , Xian Li

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Computation and Language · Computer Science 2025-09-03 Jialong Zuo , Guangyan Zhang , Minghui Fang , Shengpeng Ji , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Zhou Zhao

In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Tim Elsner , Paula Usinger , Julius Nehring-Wirxel , Gregor Kobsik , Victor Czech , Yanjiang He , Isaak Lim , Leif Kobbelt

Training Large Language Models (LLMs) at ultra-low precision is critically impeded by instability rooted in the conflict between discrete quantization constraints and the intrinsic heavy-tailed spectral nature of linguistic data. By…

Machine Learning · Computer Science 2026-02-03 Junlin Huang , Wenyi Fang , Zhenheng Tang , Yuxin Wang , Xueze Kang , Yang Zheng , Bo Li , Xiaowen Chu

DNA language models have advanced genomics, but their downstream performance varies widely due to differences in tokenization, pretraining data, and architecture. We argue that a major bottleneck lies in tokenizing sparse and unevenly…

Genomics · Quantitative Biology 2025-12-23 Xiaoxiao Zhou , Zihan Wang , Jingbo Shang , Yang E. Li

Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. However, in…

Computation and Language · Computer Science 2020-11-24 Liang Ding , Longyue Wang , Dacheng Tao

While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to…

Machine Learning · Computer Science 2025-12-29 Theo Datta , Kayla Huang , Sham Kakade , David Brandfonbrener

The prevailing maximum likelihood estimators for inferring power law models from rank-frequency data are biased. The source of this bias is an inappropriate likelihood function. The correct likelihood function is derived and shown to be…

Applications · Statistics 2021-07-27 Charlie Pilgrim , Thomas T Hills

The frequencies at which individual words occur across languages follow power law distributions, a pattern of findings known as Zipf's law. A vast literature argues over whether this serves to optimize the efficiency of human communication,…

Computation and Language · Computer Science 2020-01-16 Michael Ramscar

Currently, many studies view DNA sequences as a special type of language and utilize Transformers to model them. These studies use fixed-length k-mer segmentation and BPE subword tokenization but lack a systematic evaluation to determine…

Computation and Language · Computer Science 2025-07-22 Chenlei Gong , Yuanhe Tian , Lei Mao , Yan Song

The code base of software projects evolves essentially through inserting and removing information to and from the source code. We can measure this evolution via the elements of information - tokens, words, nodes - of the respective…

Software Engineering · Computer Science 2025-06-10 Adriano Torres , Sebastian Baltes , Christoph Treude , Markus Wagner

Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each…

Computation and Language · Computer Science 2018-09-27 Davide Nunes , Luis Antunes

Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese however can…

Computation and Language · Computer Science 2019-12-09 Changhan Wang , Kyunghyun Cho , Jiatao Gu

We study language models as evolving model organisms and ask when autoregressive next-token learning selects for world-tracking representations. For any encoding of latent world states, the Bayes-optimal next-token cross-entropy decomposes…

Methodology · Statistics 2026-04-08 Giulio Valentino Dalla Riva

In this paper, we investigate the output token probability information in the output embedding of language models. We find an approximate common log-linear encoding of output token probabilities within the output embedding vectors and…

Computation and Language · Computer Science 2024-12-12 Hakaze Cho , Yoshihiro Sakai , Kenshiro Tanaka , Mariko Kato , Naoya Inoue