English

Neural Machine Translation without Embeddings

Computation and Language 2021-04-13 v2 Machine Learning Machine Learning

Abstract

Many NLP models operate over sequences of subword tokens produced by hand-crafted tokenization rules and heuristic subword induction algorithms. A simple universal alternative is to represent every computerized text as a sequence of bytes via UTF-8, obviating the need for an embedding layer since there are fewer token types (256) than dimensions. Surprisingly, replacing the ubiquitous embedding layer with one-hot representations of each byte does not hurt performance; experiments on byte-to-byte machine translation from English to 10 different languages show a consistent improvement in BLEU, rivaling character-level and even standard subword-level models. A deeper investigation reveals that the combination of embeddingless models with decoder-input dropout amounts to token dropout, which benefits byte-to-byte models in particular.

Keywords

Cite

@article{arxiv.2008.09396,
  title  = {Neural Machine Translation without Embeddings},
  author = {Uri Shaham and Omer Levy},
  journal= {arXiv preprint arXiv:2008.09396},
  year   = {2021}
}

Comments

NAACL 2021

R2 v1 2026-06-23T18:00:51.908Z