Papers
4 articles
NLP Tokenization Benchmarks · Fertility, BLEU, and Downstream Performance
How tokenizer choices affect downstream NLP task performance — empirical benchmarks comparing BPE, Unigram, WordPiece, and character-level tokenization.
The Future of Tokenization · Beyond BPE and Unigram
Emerging tokenization research — learned tokenization, differentiable tokenizers, vision-inspired approaches, and whether tokenizers will survive the next generation of models.
Tokenization and Model Fairness · Bias in Subword Segmentation
How tokenization choices create bias in language models — the differential treatment of languages, gendered tokenization, and emerging fairness research.
The Kudo & Richardson 2018 Paper · Original SentencePiece Formulation
A summary of the SentencePiece EMNLP 2018 paper — the motivation for lossless tokenization, the BPE and Unigram implementations, and the impact on modern NLP.