Natural language often contains dependencies that span words, phrases, or even sentences. Thus, language comprehension relies on recovering recently processed information from memory for subsequent interpretation. This dissertation investigates the memory operations that subserve dependency resolution through the lens of "verb-phrase ellipsis"…

In the current millennium, extensive use of computers and the internet caused an exponential increase in information. Few research areas are as important as information extraction, which primarily involves extracting concepts and the relations between them from free text. Limitations in the size of training data, lack of lexicons and lack of…

Along with the greater productivity that CAD automation provides nowadays, the product data of engineering applications needs to be shared and managed efficiently to gain a competitive edge for the engineering product design. However, exchanging and sharing the heterogeneous product data is still challenging. This dissertation first presents a…

Computational natural language understanding and generation have been a goal of artificial intelligence since McCarthy, Minsky, Rochester and Shannon first proposed to spend the summer of 1956 studying this and related problems. Although statistical approaches dominate current natural language applications, two current research trends bring…

Since the seminal work of Gildea and Jurafsky (2000), semantic role labeling (SRL) researchers have been trying to determine the appropriate syntactic/semantic knowledge and statistical algorithms to tackle the challenges in SRL. In search of the appropriate knowledge, SRL researchers shifted from constituency grammar to dependency grammar around…

While many studies have demonstrated that conversational tutoring systems have a positive effect on learning, the amount of manual effort required to author, design, and tune dialogue behaviors remains a major barrier to widespread deployment and adoption of these systems. Such dialogue systems must not only understand student speech, but must…

Quickly accessing the contents of a video is challenging for users, particularly for unstructured video, which contains no intentional shot boundaries, no chapters, and no apparent edited format. We approach this problem in the domain of lecture videos though the use of machine learning, to gather semantic information about the videos; and through…

Coreference resolution (CR) and entity relation detection (ERD) aim at finding predefined relations between pairs of entities in text. CR focuses on resolving identity relations while ERD focuses on detecting non-identity relations. Both CR and ERD are important as they can potentially improve other natural language processing (NLP) related tasks…

In the quest for database usability, several applications enable users to design custom forms using a graphical interface, and forward engineer the forms into new databases. The path-breaking aspect of such applications is that users are completely shielded from the technicalities of database creation. Despite this innovation, the process of…

This thesis aims to define and extend a line of computational models for text comprehension that are humanly plausible. Since natural language is human by nature, computational models of human language will always be just that--models. To the degree that they miss out on information that humans would tap into, they may be improved by considering…

Firms now routinely collect information about the needs of their customers, but this information is not sufficiently considered during product design decisions. This research examines the relationship between designers and consumers to build an understanding of how the consumer should be represented to increase the consumer focus during the…

As the number of publications in the biomedical field continues its exponential increase, techniques for automatically summarizing information from this body of literature have become more diverse. In addition, the targets of summarization have become more subtle; initial work focused on extracting the factual assertions from full-text papers,…

Much recent work in natural language processing treats linguistic analysis as an inference problem over graphs. This development opens up useful connections between machine learning, graph theory, and linguistics. The first part of this dissertation formulates syntactic dependency parsing as a dynamic Markov random field with the novel…

Prior research has established an executive function advantage among bilinguals as compared to monolingual peers. These non-linguistic cognitive advantages are largely assumed to result from the experience of managing two linguistic systems. However, the possibility remains that the relationship between bilingualism and executive function is…

We consider the problem of checking whether an organization conforms to a body of regulation. Conformance is studied in a runtime verification setting. The regulation is translated to a logic, from which we synthesize monitors. The monitors are evaluated as the state of an organization evolves over time, raising an alarm if a violation is…