paper-with-me

Papers

Language Model Tokenizers Introduce Unfairness Between Languages

2023-05-17 · NeurIPS 2023 11 · Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr, Adel Bibi

Recent language models have shown impressive multilingual performance, even when not explicitly trained for it. Despite this, there are concerns about the quality of their outputs across different languages. In this paper, we show how disparity in the treatment of different languages arises at the tokenization stage, well before a model is even invoked. The same text translated into different languages can have drastically different tokenization lengths, with differences up to 15 times in some cases. These disparities persist even for tokenizers that are intentionally trained for multilingual support. Character-level and byte-level models also exhibit over 4 times the difference in the encoding length for some language pairs. This induces unfair treatment for some language communities in regard to the cost of accessing commercial language services, the processing time and latency, as well as the amount of content that can be provided as context to the models. Therefore, we make the case that we should train future language models using multilingually fair subword tokenizers.

📄 PDF Abstract BibTeX arXiv:2305.15425

Code (1)

AleksandarPetrov/tokenization-fairness 공식 구현 pytorch

Tasks

Language ModelingLanguage Modellingmodel

Similar Papers 제목 키워드 기반

Egalitarian Language Representation in Language Models: It All Begins with Tokenizers

2024-09-17 · Menan Velayuthan, Kengatharaiyer Sarveswaran

Tokenizers act as a bridge between human language and the latent space of language models, influencing how language is represented in these models. Due to the immense popularity of English-Centric Large Language Models (…

All

How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese

2023-06-16 · Takuro Fujii, Koki Shibata, Atsuki Yamaguchi, Terufumi Morishita 외

This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case st…

Impact of Tokenization on Language Models: An Analysis for Turkish

2022-04-19 · Cagri Toraman, Eyup Halit Yilmaz, Furkan Şahinuç, Oguzhan Ozcelik

Tokenization is an important text preprocessing step to prepare input tokens for deep language models. WordPiece and BPE are de facto methods employed by important models, such as BERT and GPT. However, the impact of tok…

SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers

2026-01-08 · Iaroslav Chelombitko, Ekaterina Chelombitko, Aleksey Komissarov arxiv

The quality of subword tokenization is critical for Large Language Models, yet evaluating tokenizers for morphologically rich Uralic languages is hampered by the lack of clean morpheme lexicons. We introduce SampoNLP, a …

Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?

2024-07-23 · Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh 외

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 mix…