We address the challenging task of "computational natural language inference," by which we mean bridging two or more natural language texts while also providing an explanation of how they are connected. In the context of question answering (i.e., finding short answers to natural language questions), this inference connects the question…

Much of the world's knowledge is encoded in natural language. Accessing this information would be invaluable for applications such as agent systems, question answering, the semantic web, expert systems, and many more. However, language is very ambiguous--each word in a natural language utterance can have a variety of meanings. Word sense…

The field of spoken language processing is concerned with creating computer programs that can understand human speech and produce human-like speech. Regarding the problem of understanding human speech, there is currently growing interest in moving beyond speech recognition (the task of transcribing the words in an audio stream) and towards…

This dissertation investigates the temporal relation identification task. The goal is to construct consistent temporal relations between temporal entities (e.g., events and time expressions) in a narrative. Constructing consistent temporal relations is challenging due to the exponential increase in the number of candidates for temporal relations…

The fundamental problem faced by automatic text understanding in Natural Language Processing (NLP) is to identify semantically related pieces of text and integrate them together to compute the meaning of the whole text. However, the principle of compositionality runs into trouble very quickly when real language is examined with its frequent…

In this thesis, we study the importance of background knowledge in relation extraction systems. We not only demonstrate the benefits of leveraging background knowledge to improve the systems' performance but also propose a principled framework that allows one to effectively incorporate knowledge into statistical machine learning models for…

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…

Natural language poses several challenges to developing computational systems for modeling it. Natural language is not a precise problem but is rather ridden with a number of uncertainties in the form of either alternate words or interpretations. Furthermore, natural language is a generative system where the problem size is potentially infinite.…

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…

Topic models like latent Dirichlet allocation (LDA) provide a framework for analyzing large datasets where observations are collected into groups. Although topic modeling has been fruitfully applied to problems social science, biology, and computer vision, it has been most widely used to model datasets where documents are modeled as exchangeable…