Methods › Natural Language Processing › Subword Segmentation › BPE

Byte Pair Encoding

BPE

18,975 papers tagged archive 2025-07-28

Introduced by Rico Sennrich et al. in Neural Machine Translation of Rare Words with Subword Units

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via compositional translation), and cognates and loanwords (via phonological and morphological transformations).

Lei Mao has a detailed blog post that explains how this works.

PaperSource

In Syntology about another paper, arXiv:2601.10024: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2601.10024, while the archive credits arXiv:1508.07909, so it does not say whether this method has code.

Origin paper of this answer, arXiv:2601.10024 (its page on Syntology).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 18,975 · with a code link: 8,675 · where Syntology ran a sample: 2,895 (2,353 with a run with no instrument failure, 542 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2,895 of 18,975 tagged: 2,353 with a run with no instrument failure, 542 where every run was a failure of Syntology's instrument)

Page 1 of 190: papers 1 to 100 of 18,975, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 2,351 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling2,160
Language Modeling1,675
Retrieval1,510
RAG1,346
Decoder1,232
Retrieval-augmented Generation1,166
Question Answering1,130
Translation930
Machine Translation856
Large Language Model762
Sentence712
Text Generation689
Semantic Segmentation681
Object Detection555
Image Classification534
object-detection503
Representation Learning472
Segmentation462
image-classification431
Transfer Learning417

Usage over time archive 2025-07-28

Papers per year tagged with BPE: 2015 to 2025, peak 6,130 6,130 0 2015: 1 paper 2015 2016: 2 papers 2016 2017: 23 papers 2017 2018: 122 papers 2018 2019: 584 papers 2019 2020: 1064 papers 2020 2021: 1882 papers 2021 2022: 2398 papers 2022 2023: 4305 papers 2023 2024: 6130 papers 2024 2025: 2464 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (18,975 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Subword Segmentation

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