Papers › Assessing the Importance of Frequency versus Compositionality for Subword-based...

Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT

2 Jun 2023arXiv:2306.01393archive 2025-07-28

Benoist Wolleb, Romain Silvestri, Giorgos Vernikos, Ljiljana Dolamic, Andrei Popescu-Belis

Subword tokenization is the de facto standard for tokenization in neural language models and machine translation systems. Three advantages are frequently cited in favor of subwords: shorter encoding of frequent tokens, compositionality of subwords, and ability to deal with unknown words. As their relative importance is not entirely clear yet, we propose a tokenization approach that enables us to separate frequency (the first advantage) from compositionality. The approach uses Huffman coding to tokenize words, by order of frequency, using a fixed amount of symbols. Experiments with CS-DE, EN-FR and EN-DE NMT show that frequency alone accounts for 90%-95% of the scores reached by BPE, hence compositionality has less importance than previously thought.

PaperPDFCode

Code

heig-iict-ida/huffman-tokenizer officialmentioned in paper 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

Machine TranslationNMTTranslationde-en

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