English
Related papers

Related papers: Tokenisation via Convex Relaxations

200 papers

Prior research has demonstrated noticeable performance gains through the use of probabilistic tokenizations, an approach that involves employing multiple tokenizations of the same input string during the training phase of a language model.…

Computation and Language · Computer Science 2024-07-08 Ashutosh Sathe , Divyanshu Aggarwal , Sunayana Sitaram

Subword tokenization schemes are the dominant technique used in current NLP models. However, such schemes can be rigid and tokenizers built on one corpus do not adapt well to other parallel corpora. It has also been observed that in…

Computation and Language · Computer Science 2023-06-29 Makesh Narsimhan Sreedhar , Xiangpeng Wan , Yu Cheng , Junjie Hu

When applying machine learning to problems in NLP, there are many choices to make about how to represent input texts. These choices can have a big effect on performance, but they are often uninteresting to researchers or practitioners who…

Computation and Language · Computer Science 2015-03-03 Dani Yogatama , Noah A. Smith

Unlike the matrix case, computing low-rank approximations of tensors is NP-hard and numerically ill-posed in general. Even the best rank-1 approximation of a tensor is NP-hard. In this paper, we use convex optimization to develop…

Statistics Theory · Mathematics 2016-09-14 Anil Aswani

Learning to optimize is an approach that leverages training data to accelerate the solution of optimization problems. Many approaches use unrolling to parametrize the update step and learn optimal parameters. Although L2O has shown…

Optimization and Control · Mathematics 2025-07-15 Patrick Fahy , Mohammad Golbabaee , Matthias J. Ehrhardt

The cone of positive-semidefinite (PSD) matrices is fundamental in convex optimization, and we extend this notion to tensors, defining PSD tensors, which correspond to separable quantum states. We study the convex optimization problem over…

Optimization and Control · Mathematics 2025-11-10 Liding Xu , Ye-Chao Liu , Sebastian Pokutta

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

A new approach to solving a large class of factorable nonlinear programming (NLP) problems to global optimality is presented in this paper. Unlike the traditional strategy of partitioning the decision-variable space employed in many…

Optimization and Control · Mathematics 2015-04-28 Gene A. Bunin

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

Despite the recent development in machine learning, most learning systems are still under the concept of "black box", where the performance cannot be understood and derived. With the rise of safety and privacy concerns in public, designing…

Machine Learning · Computer Science 2023-06-30 Shuai Zhang

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

Machine Learning · Computer Science 2026-02-17 Sam Dauncey , Roger Wattenhofer

Tokenization - the practice of converting strings of characters from an alphabet into sequences of tokens over a vocabulary - is a critical step in the NLP pipeline. The use of token representations is widely credited with increased model…

Computation and Language · Computer Science 2025-04-04 Juan Luis Gastaldi , John Terilla , Luca Malagutti , Brian DuSell , Tim Vieira , Ryan Cotterell

The first step in any NLP pipeline is to split the text into individual tokens. The most obvious and straightforward approach is to use words as tokens. However, given a large text corpus, representing all the words is not efficient in…

Computation and Language · Computer Science 2021-09-30 Zaid Alyafeai , Maged S. Al-shaibani , Mustafa Ghaleb , Irfan Ahmad

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

Unlike hybrid speech recognition systems where the use of tokens was restricted to phones, biphones or triphones the choice of tokens in the end-to-end ASR systems is derived from the text corpus of the training data. The use of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-06 Sunil Kumar Kopparapu , Ashish Panda

Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms…

Networking and Internet Architecture · Computer Science 2025-08-25 Zhiyuan He , Aashish Gottipati , Lili Qiu , Yuqing Yang , Francis Y. Yan

Modern ConvNets continue to achieve state-of-the-art results over a vast array of vision and image classification tasks, but at the cost of increasing parameters. One strategy for compactifying a network without sacrificing much expressive…

Machine Learning · Computer Science 2024-01-09 Tahseen Rabbani , Jiahao Su , Xiaoyu Liu , David Chan , Geoffrey Sangston , Furong Huang

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…

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

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich…

Computation and Language · Computer Science 2024-11-11 Haoran Lian , Yizhe Xiong , Zijia Lin , Jianwei Niu , Shasha Mo , Hui Chen , Peng Liu , Guiguang Ding