Extreme Adaptation for Personalized Neural Machine Translation
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.
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