Extreme Adaptation for Personalized Neural Machine Translation
This addresses the need for personalized machine translation to handle individual language variations, though it is incremental as it builds on existing adaptation methods.
The paper tackles the problem of personalizing neural machine translation to individual speaker variations by proposing a parameter-efficient adaptation technique that adjusts the output softmax bias for each user. Experiments on TED talks in three languages show improvements in translation accuracy and better reflection of speaker traits in the target text.
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.