Graphical Models with Structured Factors, Neural Factors, and Approximation-aware Training

This thesis broadens the space of rich yet practical models for structured prediction. We introduce a general framework for modeling with four ingredients: (1) latent variables, (2) structural constraints, (3) learned (neural) feature representations of the inputs, and (4) training that takes the approximations made during inference into account. The thesis builds up to this framework through an empirical study of three NLP tasks: semantic role labeling, relation extraction, and dependency parsing -- obtaining state-of-the-art results on the former two. We apply the resulting graphical models with structured and neural factors, and approximation-aware learning to jointly model part-of-speech tags, a syntactic dependency parse, and semantic roles in a low-resource setting where the syntax is unobserved. We present an alternative view of these models as neural networks with a topology inspired by inference on graphical models that encode our intuitions about the data