English

Extreme Adaptation for Personalized Neural Machine Translation

Computation and Language 2018-05-07 v1

Abstract

Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.

Keywords

Cite

@article{arxiv.1805.01817,
  title  = {Extreme Adaptation for Personalized Neural Machine Translation},
  author = {Paul Michel and Graham Neubig},
  journal= {arXiv preprint arXiv:1805.01817},
  year   = {2018}
}

Comments

Accepted as a short paper at ACL 2018

R2 v1 2026-06-23T01:45:22.680Z