Machine Translation Weekly 72: Self-Training for Zero-Shot MT
This week, I will have a look at a pre-print that describes an unconventional
setup for zero-shot machine translation. The title of the pre-print is
Self-Learning for Zero-Shot Neural Machine
Translation and was written by authors from
the University of Trento.
First of all, I have some doubt about this being really an instance of
zero-shot learning (but it is just nitpicking, the paper is interesting
regardless of the terminology). In machine learning, zero-shot learning means
that a model trained for task A is capable of doing task B without being
explicitly trained for that. An example can be: a model is trained to perform
sentiment analysis in English, but it can also do it in German because it was
trained on top of multilingual representation. This would supervised