CMU Multilingual NLP - Unsupervised Translation

CMU Multilingual NLP - Unsupervised Translation

Learn about unsupervised training methods for translation systems in this lecture from CMU's Multilingual Natural Language Processing course. Explore techniques like unsupervised word translation, back-translation, and bidirectional modeling. Examine initialization approaches using cross-lingual word embeddings and language models. Discuss the practicality of strictly unsupervised scenarios and related applications like style transfer. Gain insights into open problems and current limitations in unsupervised machine translation.