English
Related papers

Related papers: Formalizing BPE Tokenization

200 papers

Existing Machine Translation (MT) research often suggests a single, fixed set of hyperparameters for word segmentation models, symmetric Byte Pair Encoding (BPE), which applies the same number of merge operations (NMO) to train tokenizers…

Computation and Language · Computer Science 2026-02-16 Saumitra Yadav , Manish Shrivastava

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

Computation and Language · Computer Science 2025-04-15 Buu Phan , Brandon Amos , Itai Gat , Marton Havasi , Matthew Muckley , Karen Ullrich

Speech tokenization is crucial in digital speech processing, converting continuous speech signals into discrete units for various computational tasks. This paper introduces a novel speech tokenizer with broad applicability across downstream…

Machine Learning · Computer Science 2025-07-10 Wonjin Jung , Sungil Kang , Dong-Yeon Cho

We describe an LSTM-based model which we call Byte-to-Span (BTS) that reads text as bytes and outputs span annotations of the form [start, length, label] where start positions, lengths, and labels are separate entries in our vocabulary.…

Computation and Language · Computer Science 2016-04-05 Dan Gillick , Cliff Brunk , Oriol Vinyals , Amarnag Subramanya

Byte-level fallbacks for subword tokenization have become a common practice in large language models. In particular, it has been demonstrated to be incredibly effective as a pragmatic solution for preventing OOV, especially in the context…

Computation and Language · Computer Science 2025-06-10 Sangwhan Moon , Tatsuya Hiraoka , Naoaki Okazaki

Finding an optimal word representation algorithm is particularly important in terms of domain specific data, as the same word can have different meanings and hence, different representations depending on the domain and context. While…

Computation and Language · Computer Science 2025-10-09 Nouman Ahmed , Ronin Wu , Victor Botev

Subword tokenization is the de facto standard for tokenization in neural language models and machine translation systems. Three advantages are frequently cited in favor of subwords: shorter encoding of frequent tokens, compositionality of…

Computation and Language · Computer Science 2024-01-15 Benoist Wolleb , Romain Silvestri , Giorgos Vernikos , Ljiljana Dolamic , Andrei Popescu-Belis

Tokenization is fundamental to how language models represent and process text, yet the behavior of widely used BPE tokenizers has received far less study than model architectures and training. In this paper, we investigate intermediate…

Computation and Language · Computer Science 2026-02-05 Yike Sun , Haotong Yang , Zhouchen Lin , Muhan Zhang

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

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

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

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

Computation and Language · Computer Science 2025-06-03 Shunsuke Kando , Yusuke Miyao , Shinnosuke Takamichi

Byte-based machine translation systems have shown significant potential in massively multilingual settings. Unicode encoding, which maps each character to specific byte(s), eliminates the emergence of unknown words, even in new languages.…

Computation and Language · Computer Science 2025-02-10 Langlin Huang , Mengyu Bu , Yang Feng

Large language models route every input through a learned embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainable parameters at frontier scale. We introduce Kronecker Embeddings, a deterministic…

Computation and Language · Computer Science 2026-05-29 Rohan Shravan

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued,…

Computation and Language · Computer Science 2019-06-21 Dinghan Shen , Pengyu Cheng , Dhanasekar Sundararaman , Xinyuan Zhang , Qian Yang , Meng Tang , Asli Celikyilmaz , Lawrence Carin

Phones and their context-dependent variants have been the standard modeling units for conventional speech recognition systems, while characters and subwords have demonstrated their effectiveness for end-to-end recognition systems. We…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-23 Weiran Wang , Guangsen Wang , Aadyot Bhatnagar , Yingbo Zhou , Caiming Xiong , Richard Socher

Common subword tokenization algorithms like BPE and UnigramLM assume that text can be split into meaningful units by concatenative measures alone. This is not true for languages such as Hebrew and Arabic, where morphology is encoded in…

Computation and Language · Computer Science 2025-06-04 Bar Gazit , Shaltiel Shmidman , Avi Shmidman , Yuval Pinter

The Space-Air-Ground-Sea integrated network calls for more robust and secure transmission techniques against jamming. In this paper, we propose a textual semantic transmission framework for robust transmission, which utilizes the advanced…

Computation and Language · Computer Science 2023-07-25 Shicong Liu , Zhen Gao , Gaojie Chen , Yu Su , Lu Peng

Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To…

Computation and Language · Computer Science 2020-10-21 Haohan Wang , Peiyan Zhang , Eric P. Xing

Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…

Computation and Language · Computer Science 2024-10-07 Yekun Chai , Yewei Fang , Qiwei Peng , Xuhong Li