Joint multilingual learning for coreference resolution


Abstract

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 thesis, I present 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 dis- covering linguistic information shared across languages at the granular level of a sentence. The coreference resolution system is one of the first attempts at joint mul- tilingual modeling of named entity recognition and coreference resolution with limited linguistic resources. It performs second best on three out of four languages when com- pared to state-of-the-art systems built with rich linguistic resources. I show that we can simultaneously model both the depth and the breadth of natural languages using the underlying linguistic structure shared across languages.

Resources: annotated multilingual corpus

Code