Subword Segmentation

Byte Pair Encoding

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

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.

Source: Neural Machine Translation of Rare Words with Subword Units


Paper Code Results Date Stars


Task Papers Share
Language Modelling 49 6.19%
Object Detection 40 5.06%
Semantic Segmentation 35 4.42%
Image Classification 29 3.67%
Text Generation 18 2.28%
Machine Translation 18 2.28%
Question Answering 17 2.15%
Self-Supervised Learning 12 1.52%
Denoising 10 1.26%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign