Il prossimoProssima guida
Tokenizzazione e codifica della coppia di byte
Tecnico
GUIDA ALL'AI linguistica
Byte-pair encoding builds larger symbols by repeatedly merging frequent adjacent pairs during training.
Ascolta questa guidaNarrato dall'IA · ~3 min
Its learned vocabulary and merge priorities support subword encoding, while byte-level variants use a byte alphabet rather than a character-only base.
BPE was developed for data compression and adapted to word segmentation in the translation research by Sennrich, Haddow, and Birch, published in 2016. In a common subword-training procedure, text is represented through initial symbols such as characters. Adjacent pairs are counted over the training representation, and a frequent pair is merged into a larger symbol. Repeating the procedure learns reusable pieces. More frequent sequences can gain larger units, while an unfamiliar word may remain split into smaller ones. The precise behavior depends on the training data and implementation; not every common word must become one token. Training produces a vocabulary and an ordered collection of merge rules. GPT-2's published encoder applies eligible pairs according to learned ranks rather than recounting the new input to invent a new vocabulary. It first represents UTF-8 bytes through a reversible byte-to-symbol mapping. The byte alphabet covers 256 values, permitting valid UTF-8 input to be represented through its constituent bytes when larger merged pieces are unavailable. This avoids the character-alphabet coverage limitation under that configuration, but encoding success does not establish that the model knows the text's meaning. Vocabulary accounting can be explicit. In an illustrative configuration with 256 base byte tokens, two distinct additional merge tokens, and one separate special token, the total is 259. Decoding has another important order: GPT-2's implementation joins decoded token pieces, reconstructs the complete byte sequence, then decodes that sequence as UTF-8. Individual pieces need not each correspond to an independently complete Unicode character.
Studying the BPE word-segmentation method in Sennrich and colleagues' translation research.
Inspecting GPT-2's published byte mapping and ranked merge implementation.
Calculating vocabulary size for a stated base, unique merges, and special-token allocation.
Reconstructing a byte sequence before decoding its UTF-8 text.
BPE configurations can be compared through sequence lengths, coverage, and effects on a trained model rather than assumed to be optimal for every language or input type. Changes to the byte alphabet, preprocessing, vocabulary, or merge rules alter the actual encoding. A reproducible comparison should preserve those details and identify any normalization applied before tokenization. Other segmentation methods offer different design choices, while byte-level coverage remains distinct from semantic understanding. Inspecting the learned pieces and reconstruction process is useful for diagnosing representational behavior without attributing every model failure to BPE alone.
Newsletter gratuita
Tre storie verificate sull'IA ogni mattina nei giorni feriali, scritte in un inglese semplice. Gratuito per sempre, senza pubblicità.
Un'email ogni giorno feriale. Disiscriviti con un clic. Non vendiamo né condividiamo mai il tuo indirizzo.
Mettiti alla prova
Feedback immediato su ogni risposta e un certificato condivisibile con un ID verificabile una volta superato un corso.
Sostieni l'istruzione gratuita sull'IA. AI Understanding è un'organizzazione non profit 501(c)(3) — nessun annuncio, nessun paywall, mai. Fai una donazione
Byte-pair encoding builds larger symbols by repeatedly merging frequent adjacent pairs during training. Its learned vocabulary and merge priorities support subword encoding, while byte-level variants use a byte alphabet rather than a character-only base.
The training procedure counts adjacent symbol pairs and learns merges; encoding later uses the saved rules.
BPE inizia dalle unità più piccole (caratteri o byte grezzi) e fa crescere token più grandi attraverso le fusioni.
The complete byte alphabet supplies the stated fallback; this does not apply to every character-only subword vocabulary.
BPE è stato introdotto come tecnica di compressione dei dati nel 1994 e successivamente adattato per la tokenizzazione delle sottoparole nel 2016.
Its implementation selects eligible pairs through saved BPE ranks rather than re-learning corpus frequencies at encoding time.
Continua a imparare
Altre guide selezionate per questo argomento
Il prossimoProssima guida
Tokenizzazione e codifica della coppia di byte
Tecnico