Can it be possible to train a neural network with no parallel bilingual data?
In this paper: Unsupervised Machine Translation Using Monolingual Corpora Only the authors proposed a novel method.
Intuitively it is an autoencoder, but the Start Of Sentence token is set to be the language type.
One other advanced method is to use the pre-training model. In this paper: Cross-lingual Language Model Pretraining researchers proposed an algorithm that utilized the pre-trained multi-lingual trained BERT(with labeled data but we don't need to have a labeled dataset for our task) and the autoencoder mentioned previously.