ByteSpan: Information-Driven Subword Tokenisation
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:B6QMVEAVrecord.jsonopen to challenge →
read the original abstract
Recent dynamic tokenisation methods operate directly on bytes and pool their latent representations into patches. This bears similarities to computational models of word segmentation that determine lexical boundaries using spikes in an autoregressive model's prediction error. Inspired by this connection, we explore whether grouping predictable bytes - rather than pooling their representations - can yield a useful fixed subword vocabulary. We propose a new information-driven subword tokeniser, ByteSpan, that uses an external byte-level LM during training to identify contiguous predictable byte sequences and group them into subwords. Experiments show that ByteSpan yields efficient vocabularies with higher morphological alignment scores than BPE for English. Multilingual experiments show similar compression and R\'enyi efficiency for 25 languages.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Faster Superword Tokenization
Frequency aggregation of supermerge candidates and a two-phase formulation make BoundlessBPE and SuperBPE training over 600x faster on 1GB data while preserving identical results, with open-source Python and Rust code.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.