Papers › A Formal Perspective on Byte-Pair Encoding

A Formal Perspective on Byte-Pair Encoding

29 Jun 2023arXiv:2306.16837archive 2025-07-28

Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Tim Vieira, Mrinmaya Sachan, Ryan Cotterell

Byte-Pair Encoding (BPE) is a popular algorithm used for tokenizing data in NLP, despite being devised initially as a compression method. BPE appears to be a greedy algorithm at face value, but the underlying optimization problem that BPE seeks to solve has not yet been laid down. We formalize BPE as a combinatorial optimization problem. Via submodular functions, we prove that the iterative greedy version is a 1/(σ(μ^⋆))(1-e^(-σ(μ^⋆)))-approximation of an optimal merge sequence, where σ(μ^⋆) is the total backward curvature with respect to the optimal merge sequence μ^⋆. Empirically the lower bound of the approximation is ≈0.37. We provide a faster implementation of BPE which improves the runtime complexity from 𝒪(N M) to 𝒪(N logM), where N is the sequence length and M is the merge count. Finally, we optimize the brute-force algorithm for optimal BPE using memoization.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zouharvi/formal-bpe officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Combinatorial Optimization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BPE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections