Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier



Open Access Dissertation

Document Type


Degree Name

Doctor of Philosophy (PhD)

Degree Program

Computer Science

Year Degree Awarded


Month Degree Awarded


First Advisor

David A. Smith

Second Advisor

Mark Johnson

Subject Categories

Artificial Intelligence and Robotics | Computer Sciences


Constructing end-to-end NLP systems requires the processing of many types of linguistic information prior to solving the desired end task. A common approach to this problem is to construct a pipeline, one component for each task, with each system's output becoming input for the next. This approach poses two problems. First, errors propagate, and, much like the childhood game of "telephone", combining systems in this manner can lead to unintelligible outcomes. Second, each component task requires annotated training data to act as supervision for training the model. These annotations are often expensive and time-consuming to produce, may differ from each other in genre and style, and may not match the intended application. In this dissertation we present a general framework for constructing and reasoning on joint graphical model formulations of NLP problems. Individual models are composed using weighted Boolean logic constraints, and inference is performed using belief propagation. The systems we develop are composed of two parts: one a representation of syntax, the other a desired end task (semantic role labeling, named entity recognition, or relation extraction). By modeling these problems jointly, both models are trained in a single, integrated process, with uncertainty propagated between them. This mitigates the accumulation of errors typical of pipelined approaches. Additionally we propose a novel marginalization-based training method in which the error signal from end task annotations is used to guide the induction of a constrained latent syntactic representation. This allows training in the absence of syntactic training data, where the latent syntactic structure is instead optimized to best support the end task predictions. We find that across many NLP tasks this training method offers performance comparable to fully supervised training of each individual component, and in some instances improves upon it by learning latent structures which are more appropriate for the task.