Pith. sign in

REVIEW 1 cited by

BPE-Dropout: Simple and Effective Subword Regularization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1910.13267 v2 pith:KPJTCD75 submitted 2019-10-29 cs.CL

classification cs.CL
keywords subwordsegmentationmultiplebpe-dropoutregularizationsamesegmentationswords
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Subword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent words intact while splitting the rare ones into multiple tokens. While multiple segmentations are possible even with the same vocabulary, BPE splits words into unique sequences; this may prevent a model from better learning the compositionality of words and being robust to segmentation errors. So far, the only way to overcome this BPE imperfection, its deterministic nature, was to create another subword segmentation algorithm (Kudo, 2018). In contrast, we show that BPE itself incorporates the ability to produce multiple segmentations of the same word. We introduce BPE-dropout - simple and effective subword regularization method based on and compatible with conventional BPE. It stochastically corrupts the segmentation procedure of BPE, which leads to producing multiple segmentations within the same fixed BPE framework. Using BPE-dropout during training and the standard BPE during inference improves translation quality up to 3 BLEU compared to BPE and up to 0.9 BLEU compared to the previous subword regularization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Comparative analysis of subword tokenization approaches for Indian languages

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Across SMT and NMT models for 11 Indian languages, SentencePiece gives the highest BLEU for most language pairs, while BPE wins in the multilingual model.

Pith tools