English
Related papers

Related papers: Comparative analysis of subword tokenization appro…

200 papers

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially…

Computation and Language · Computer Science 2025-04-29 Gunjan Balde , Soumyadeep Roy , Mainack Mondal , Niloy Ganguly

Past vocabulary learning techniques identify relevant vocabulary before training, relying on statistical and entropy-based assumptions that largely neglect the role of model training. Empirically, we observe that trained translation models…

Computation and Language · Computer Science 2025-04-02 Pin-Jie Lin , Ernie Chang , Yangyang Shi , Vikas Chandra

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair…

Machine Learning · Statistics 2017-07-06 Bart van Merriënboer , Amartya Sanyal , Hugo Larochelle , Yoshua Bengio

Tokenization constitutes a fundamental stage in Large Language Model (LLM) processing; however, subword-based tokenization methods optimized on English-dominant corpora may produce token fragmentation misaligned with the linguistic…

Computers and Society · Computer Science 2026-02-10 Andhika Bernard Lumbantobing , Hokky Situngkir

In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Tim Elsner , Paula Usinger , Julius Nehring-Wirxel , Gregor Kobsik , Victor Czech , Yanjiang He , Isaak Lim , Leif Kobbelt

Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to…

Computation and Language · Computer Science 2025-02-11 Katharina Hämmerl , Tomasz Limisiewicz , Jindřich Libovický , Alexander Fraser

Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-dimensional representations used in various contexts, from…

Software Engineering · Computer Science 2025-07-22 Mootez Saad , Hao Li , Tushar Sharma , Ahmed E. Hassan

When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different…

Machine Learning · Computer Science 2023-11-14 Nathan Fradet , Nicolas Gutowski , Fabien Chhel , Jean-Pierre Briot

Language model pre-training based on large corpora has achieved tremendous success in terms of constructing enriched contextual representations and has led to significant performance gains on a diverse range of Natural Language…

Computation and Language · Computer Science 2021-08-04 Weidong Guo , Mingjun Zhao , Lusheng Zhang , Di Niu , Jinwen Luo , Zhenhua Liu , Zhenyang Li , Jianbo Tang

Large Language Models have proven highly successful at modelling a variety of tasks. However, this comes at a steep computational cost that hinders wider industrial uptake. In this paper, we present MWT: a Multi-Word Tokenizer that goes…

Computation and Language · Computer Science 2024-04-08 Leonidas Gee , Leonardo Rigutini , Marco Ernandes , Andrea Zugarini

A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy is usually used to…

Computation and Language · Computer Science 2022-09-13 Shiyue Zhang , Vishrav Chaudhary , Naman Goyal , James Cross , Guillaume Wenzek , Mohit Bansal , Francisco Guzman

Cross-lingual vocabulary transfer plays a promising role in adapting pre-trained language models to new languages, including low-resource languages. Existing approaches that utilize monolingual or parallel corpora face challenges when…

Computation and Language · Computer Science 2025-06-03 Haruki Sakajo , Yusuke Ide , Justin Vasselli , Yusuke Sakai , Yingtao Tian , Hidetaka Kamigaito , Taro Watanabe

Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While linguistically-motivated tokenization techniques were shown to have significant effects on the performance of statistical MT, it…

Computation and Language · Computer Science 2019-06-28 Mai Oudah , Amjad Almahairi , Nizar Habash

Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that…

Computation and Language · Computer Science 2025-08-26 Andrei-Valentin Tănase , Elena Pelican

English to Indian language machine translation poses the challenge of structural and morphological divergence. This paper describes English to Indian language statistical machine translation using pre-ordering and suffix separation. The…

Computation and Language · Computer Science 2018-08-03 Raj Nath Patel , Prakash B. Pimpale , M Sasikumar

Subword regularization methods such as BPE dropout are typically applied only during fine-tuning, while pretraining is usually done with deterministic tokenization. This creates a potential segmentation mismatch between pretraining and…

Computation and Language · Computer Science 2026-05-14 Ruan Visser , Trienko Grobler , Marcel Dunaiski

In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach…

Computation and Language · Computer Science 2018-10-23 Elizabeth Salesky , Andrew Runge , Alex Coda , Jan Niehues , Graham Neubig

Subword regularizations use multiple subword segmentations during training to improve the robustness of neural machine translation models. In previous subword regularizations, we use multiple segmentations in the training process but use…

Computation and Language · Computer Science 2022-03-28 Sho Takase , Tatsuya Hiraoka , Naoaki Okazaki

Multilingual language models have shown impressive cross-lingual transfer ability across a diverse set of languages and tasks. To improve the cross-lingual ability of these models, some strategies include transliteration and finer-grained…

Computation and Language · Computer Science 2023-05-08 Sonal Sannigrahi , Rachel Bawden

Subword-level understanding is integral to numerous tasks, including understanding multi-digit numbers, spelling mistakes, abbreviations, rhyming, and wordplay. Despite this, current large language models (LLMs) still struggle…

Computation and Language · Computer Science 2026-04-22 Anya Sims , Thom Foster , Klara Kaleb , Tuan-Duy H. Nguyen , Joseph Lee , Jakob N. Foerster , Yee Whye Teh , Cong Lu