Scaling Language Understanding via Joint Multilingual Learning

Natural language is a pervasive human skill not yet fully achievable by automated computing systems. The main challenge is understanding how to computationally model both the depth and the breadth of natural languages.

In this talk, Andreea Bodnari (Chief Data Scientist at Movable Ink) presents two probabilistic models that systematically model both the depth and the breadth of natural languages for two different linguistic tasks: syntactic parsing and joint learning of named entity recognition and coreference resolution.

The syntactic parsing model outperforms current state of the art models by discovering linguistic information shared across languages at the granular level of a sentence. The coreference resolution system is one of the first attempts at joint multilingual modeling of named entity recognition and coreference resolution with limited linguistic resources. It performs second best on three out of four languages when compared to state of the art systems built with rich linguistic resources. Andreea shows that we can simultaneously model both the depth and the breadth of natural languages using the underlying linguistic structure shared across languages.

47:37

This talk was filmed at the NYC Machine Learning at Pivotal Labs.