Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer

Understand

Natural language processing is heavily Anglo-centric, while the demand for models that work in languages other than English is greater than ever.

• Yet, the task of transferring a model from one language to another can be expensive in terms of annotation costs, engineering time and effort.
• In this paper, we present a general framework for easily and effectively transferring neural models from English to other languages.
• The framework, which relies on task representations as a form of weak supervision, is model and task agnostic, meaning that many existing neural architectures can be ported to other languages with minimal effort.