Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models

Understand

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings.

• The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as an input.
• The proposed model contains bidirectional LSTMs that perform as forward and backward language models, and these networks are shared among all the languages.
• The other parameters, i.e.