English
Related papers

Related papers: BPE Stays on SCRIPT: Structured Encoding for Robus…

200 papers

Pretokenization is a crucial, sequential pass in Byte-level BPE tokenizers, yet little work has been done to optimize it for edge-side inference. Our proposed new implementation, Peek2, serves as a drop-in replacement for cl100k-like…

Computation and Language · Computer Science 2026-05-04 Liu Zai , Iraklis Klampanos

The assumption across nearly all language model (LM) tokenization schemes is that tokens should be subwords, i.e., contained within word boundaries. While providing a seemingly reasonable inductive bias, is this common practice limiting the…

Computation and Language · Computer Science 2025-08-28 Alisa Liu , Jonathan Hayase , Valentin Hofmann , Sewoong Oh , Noah A. Smith , Yejin Choi

The relationship between tokenizer algorithm (e.g., Byte-Pair Encoding (BPE), Unigram), morphological alignment, tokenization quality (e.g., compression efficiency), and downstream performance remains largely unclear, particularly for…

Computation and Language · Computer Science 2025-11-11 Saketh Reddy Vemula , Sandipan Dandapat , Dipti Misra Sharma , Parameswari Krishnamurthy

The pretraining data of today's strongest language models is opaque; in particular, little is known about the proportions of various domains or languages represented. In this work, we tackle a task which we call data mixture inference,…

Computation and Language · Computer Science 2024-12-03 Jonathan Hayase , Alisa Liu , Yejin Choi , Sewoong Oh , Noah A. Smith

We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and for some languages…

Computation and Language · Computer Science 2017-10-09 Benjamin Heinzerling , Michael Strube

Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but driven by statistics rather than grammar. As a result,…

Computation and Language · Computer Science 2025-10-17 Yinxi Li , Yuntian Deng , Pengyu Nie

We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not…

Computation and Language · Computer Science 2024-04-02 Marco Cognetta , Tatsuya Hiraoka , Naoaki Okazaki , Rico Sennrich , Yuval Pinter

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…

A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts. Although contemporary text encoding methods cover most of the world's writing systems, they exhibit bias…

Computation and Language · Computer Science 2024-11-12 Tomasz Limisiewicz , Terra Blevins , Hila Gonen , Orevaoghene Ahia , Luke Zettlemoyer

Tokenization is a critical component of Natural Language Processing (NLP), especially for low resource languages, where subword segmentation influences vocabulary structure and downstream task accuracy. Although Byte Pair Encoding (BPE) is…

Computation and Language · Computer Science 2025-04-25 Priyaranjan Pattnayak , Hitesh Laxmichand Patel , Amit Agarwal

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

Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Recent developments in binary-level foundation models suggest a…

Cryptography and Security · Computer Science 2026-05-19 Saastha Vasan , Yuzhou Nie , Kaie Chen , Yigitcan Kaya , Hojjat Aghakhani , Roman Vasilenko , Wenbo Guo , Christopher Kruegel , Giovanni Vigna

In this paper, we aim to do code completion based on implementing a Neural Network from Li et. al.. Our contribution is that we use an encoding that is in-between character and word encoding called Byte Pair Encoding (BPE). We use this on…

Computation and Language · Computer Science 2020-04-15 Youri Arkesteijn , Nikhil Saldanha , Bastijn Kostense

Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by breaking down words…

Computation and Language · Computer Science 2025-05-23 Sudhansu Bala Das , Samujjal Choudhury , Tapas Kumar Mishra , Bidyut Kr. Patra

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear. In this paper, we argue for the theoretical importance of compression, that can be…

Computation and Language · Computer Science 2024-06-25 Omer Goldman , Avi Caciularu , Matan Eyal , Kris Cao , Idan Szpektor , Reut Tsarfaty

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 explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best…

Computation and Language · Computer Science 2017-07-24 Anoop Kunchukuttan , Pushpak Bhattacharyya

Tokenization is widely used in large language models because it significantly improves performance. However, tokenization imposes several disadvantages, such as performance biases, increased adversarial vulnerability, decreased…

Computation and Language · Computer Science 2024-10-08 Kevin Slagle

Tokenization is the first - and often underappreciated - layer of computation in language models. While Chain-of-Thought (CoT) prompting enables transformer models to approximate recurrent computation by externalizing intermediate steps, we…

Computation and Language · Computer Science 2025-05-21 Xiang Zhang , Juntai Cao , Jiaqi Wei , Yiwei Xu , Chenyu You

This paper presents a comprehensive examination of the impact of tokenization strategies and vocabulary sizes on the performance of Arabic language models in downstream natural language processing tasks. Our investigation focused on the…

Computation and Language · Computer Science 2024-09-23 Mohamed Taher Alrefaie , Nour Eldin Morsy , Nada Samir