English
Related papers

Related papers: Faster Superword Tokenization

200 papers

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak…

Computation and Language · Computer Science 2026-04-16 Pavel Chizhov , Egor Bogomolov , Ivan P. Yamshchikov

Tokenization is a fundamental preprocessing step for almost all NLP tasks. In this paper, we propose efficient algorithms for the WordPiece tokenization used in BERT, from single-word tokenization to general text (e.g., sentence)…

Computation and Language · Computer Science 2021-10-07 Xinying Song , Alex Salcianu , Yang Song , Dave Dopson , Denny Zhou

In this paper, we investigate how the output representation of an end-to-end neural network affects multilingual automatic speech recognition (ASR). We study different representations including character-level, byte-level, byte pair…

Computation and Language · Computer Science 2022-05-03 Liuhui Deng , Roger Hsiao , Arnab Ghoshal

The pre-trained language models have achieved great successes in various natural language understanding (NLU) tasks due to its capacity to capture the deep contextualized information in text by pre-training on large-scale corpora. One of…

Computation and Language · Computer Science 2021-06-04 Junqiu Wei , Qun Liu , Yinpeng Guo , Xin Jiang

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

We present frequency-ordered tokenization, a simple preprocessing technique that improves lossless text compression by exploiting the power-law frequency distribution of natural language tokens (Zipf's law). The method tokenizes text with…

Information Theory · Computer Science 2026-02-27 Maximilian Kalcher

Tokenizer adaptation plays an important role in adapting pre-trained language models to new domains or languages. In this work, we address two complementary aspects of this process: vocabulary extension and pruning. The common approach to…

Computation and Language · Computer Science 2026-03-24 Taido Purason , Pavel Chizhov , Ivan P. Yamshchikov , Mark Fishel

The challenges facing speech recognition systems, such as variations in pronunciations, adverse audio conditions, and the scarcity of labeled data, emphasize the necessity for a post-processing step that corrects recurring errors. Previous…

Computation and Language · Computer Science 2023-10-18 Tomer Wullach , Shlomo E. Chazan

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Computation and Language · Computer Science 2022-10-07 Mario Michael Krell , Matej Kosec , Sergio P. Perez , Andrew Fitzgibbon

This study investigates the impact of morphological typology on tokenization and language modeling performance. We focus on languages with synthetic and analytical morphological structures and examine their productivity when tokenized using…

Computation and Language · Computer Science 2024-11-01 Iñigo Parra

As large language models move toward million-token context windows, CPU tokenizers become a major slowdown because they process text one step at a time while powerful GPUs sit unused. We built a GPU-based byte-level BPE tokenizer that…

Computation and Language · Computer Science 2026-03-04 Venu Gopal Kadamba , Kanishkha Jaisankar

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

NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization…

Computation and Language · Computer Science 2017-09-06 Aleš Tamchyna , Marion Weller-Di Marco , Alexander Fraser

Tokenization is used almost universally by modern language models, enabling efficient text representation using multi-byte or multi-character tokens. However, prior work has shown that tokenization can introduce distortion into the model's…

Computation and Language · Computer Science 2026-05-08 Jonathan Hayase , Alisa Liu , Noah A. Smith , Sewoong Oh

As the ever-increasing token limits of large language models (LLMs) have enabled long context as input, prompting with single data samples might no longer an efficient way. A straightforward strategy improving efficiency is to batch data…

Computation and Language · Computer Science 2024-07-16 Jianzhe Lin , Maurice Diesendruck , Liang Du , Robin Abraham

We present automatic speech recognition (ASR) systems for Tamil and Kannada based on subword modeling to effectively handle unlimited vocabulary due to the highly agglutinative nature of the languages. We explore byte pair encoding (BPE),…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-28 Madhavaraj A , Bharathi Pilar , Ramakrishnan A G

Regular expression is important for many natural language processing tasks especially when used to deal with unstructured and semi-structured data. This work focuses on automatically generating regular expressions and proposes a novel…

Neural and Evolutionary Computing · Computer Science 2020-06-25 Desheng Wang , Jiawei Liu , Xiang Qi , Baolin Sun , Peng Zhang

The cold-start issue is the challenge when we talk about recommender systems, especially in the case when we do not have the past interaction data of new users or new items. Content-based features or hybrid solutions are common as…

Information Retrieval · Computer Science 2025-09-17 Yushang Zhao , Xinyue Han , Qian Leng , Qianyi Sun , Haotian Lyu , Chengrui Zhou

Tokenization underlies every large language model, yet it remains an under-theorized and inconsistently designed component. Common subword approaches such as Byte Pair Encoding (BPE) offer scalability but often misalign with linguistic…

Computation and Language · Computer Science 2026-01-27 Sawsan Alqahtani , Mir Tafseer Nayeem , Md Tahmid Rahman Laskar , Tasnim Mohiuddin , M Saiful Bari

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…