Cross-lingual language model
Year: 2,019
Journal: Conference on Neural Information Processing Systems
Languages: Arabic, Bulgarian, Chinese, English, French, German, Greek, Hindi, Russian, Spanish, Swahili, Thai, Turkish, Urdu, Vietnamese
Programming languages: Python
Input data:
sentences
Project website: https://github.com/facebookresearch/XLM/
We propose two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross-lingual language model objective.