English
Related papers

Related papers: Sub-Character Tokenization for Chinese Pretrained …

200 papers

Simplified Chinese to Traditional Chinese character conversion is a common preprocessing step in Chinese NLP. Despite this, current approaches have poor performance because they do not take into account that a simplified Chinese character…

Computation and Language · Computer Science 2020-05-08 Pranav A , Isabelle Augenstein

Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…

Computation and Language · Computer Science 2025-06-11 Tim Vieira , Ben LeBrun , Mario Giulianelli , Juan Luis Gastaldi , Brian DuSell , John Terilla , Timothy J. O'Donnell , Ryan Cotterell

Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…

Computation and Language · Computer Science 2023-10-19 Avijit Thawani , Saurabh Ghanekar , Xiaoyuan Zhu , Jay Pujara

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here,…

Computation and Language · Computer Science 2022-06-07 Ayush Kaushal , Kyle Mahowald

Character-level language models obviate the need for separately trained tokenizers, but efficiency suffers from longer sequence lengths. Learning to combine character representations into tokens has made training these models more…

Computation and Language · Computer Science 2023-11-16 William Fleshman , Benjamin Van Durme

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword…

Computation and Language · Computer Science 2026-05-15 Théo Gigant , Bowen Peng , Jeffrey Quesnelle

The pre-training of text encoders normally processes text as a sequence of tokens corresponding to small text units, such as word pieces in English and characters in Chinese. It omits information carried by larger text granularity, and thus…

Computation and Language · Computer Science 2019-11-05 Shizhe Diao , Jiaxin Bai , Yan Song , Tong Zhang , Yonggang Wang

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens. In this work, we…

Computation and Language · Computer Science 2025-06-13 Tatsuya Hiraoka , Kentaro Inui

Chinese Spell Checking (CSC) aims to detect and correct spelling errors in sentences. Despite Large Language Models (LLMs) exhibit robust capabilities and are widely applied in various tasks, their performance on CSC is often…

Computation and Language · Computer Science 2024-10-29 Kunting Li , Yong Hu , Liang He , Fandong Meng , Jie Zhou

Characters have commonly been regarded as the minimal processing unit in Natural Language Processing (NLP). But many non-latin languages have hieroglyphic writing systems, involving a big alphabet with thousands or millions of characters.…

Computation and Language · Computer Science 2018-01-08 Han He , Lei Wu , Xiaokun Yang , Hua Yan , Zhimin Gao , Yi Feng , George Townsend

The Backpack is a Transformer alternative shown to improve interpretability in English language modeling by decomposing predictions into a weighted sum of token sense components. However, Backpacks' reliance on token-defined meaning raises…

Computation and Language · Computer Science 2023-10-20 Hao Sun , John Hewitt

Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of…

Computation and Language · Computer Science 2024-09-11 Arnon Turetzky , Yossi Adi

Large pretrained language models (PLMs) typically tokenize the input string into contiguous subwords before any pretraining or inference. However, previous studies have claimed that this form of subword tokenization is inadequate for…

Computation and Language · Computer Science 2022-04-12 Omri Keren , Tal Avinari , Reut Tsarfaty , Omer Levy

Relative to English, low-resource languages suffer from substantial tokenization premiums in modern LMs, meaning that it generally requires several times as many tokens to encode a sentence in a low-resource language than to encode the…

Computation and Language · Computer Science 2026-01-21 Geoffrey Churchill , Steven Skiena

Commonly-used transformer language models depend on a tokenization schema which sets an unchangeable subword vocabulary prior to pre-training, destined to be applied to all downstream tasks regardless of domain shift, novel word formations,…

Computation and Language · Computer Science 2021-08-03 Yuval Pinter , Amanda Stent , Mark Dredze , Jacob Eisenstein

Language models (LMs) have been reported to implicitly encode character-level information, despite not being explicitly provided during training. However, the mechanisms underlying this phenomenon remain largely unexplored. To reveal the…

Computation and Language · Computer Science 2026-02-06 Soma Sato , Ryohei Sasano

Neural machine translation (NMT) is one of the best methods for understanding the differences in semantic rules between two languages. Especially for Indo-European languages, subword-level models have achieved impressive results. However,…

Computation and Language · Computer Science 2019-11-11 Wei Zhang , Feifei Lin , Xiaodong Wang , Zhenshuang Liang , Zhen Huang

Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed…

Computation and Language · Computer Science 2018-09-11 Falcon Z. Dai , Zheng Cai

Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…

Computation and Language · Computer Science 2024-04-09 Yilin Wang , Xinyi Hu , Matthew R. Gormley

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Computation and Language · Computer Science 2026-02-04 Brian Siyuan Zheng , Alisa Liu , Orevaoghene Ahia , Jonathan Hayase , Yejin Choi , Noah A. Smith
‹ Prev 1 2 3 10 Next ›