{N}eural {M}achine {T}ranslation of {R}are {W}ords with {S}ubword {U}nits

  • Sennrich R
  • Haddow B
  • Birch A
Citations of this article
Mendeley users who have this article in their library.


Neural machine translation (NMT) models typically operate with a fixed vocabulary , but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper , we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via com-positional translation), and cognates and loanwords (via phonological and morphological transformations). We discuss the suitability of different word segmentation techniques, including simple character n-gram models and a segmentation based on the byte pair encoding compression algorithm , and empirically show that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English→German and English→Russian by up to 1.1 and 1.3 BLEU, respectively.




Sennrich, R., Haddow, B., & Birch, A. (2015). {N}eural {M}achine {T}ranslation of {R}are {W}ords with {S}ubword {U}nits. ArXiv:1507.07909, 1715–1725. Retrieved from http://www.aclweb.org/anthology/P16-1162.pdf

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free