To build an Artificial Intelligence system that can assist us in daily lives, the ability to understand the world around us through visual input is essential. Prior studies train visual perception models by defining concept vocabularies and annotate data against the fixed vocabulary. It is hard to define a comprehensive set of everything, and thus…

Humans have the remarkable ability to solve different tasks by simply reading textual instructions that define the tasks and looking at a few examples. Natural Language Processing (NLP) models built with the conventional machine learning paradigm, however, often struggle to generalize across tasks (e.g., a question-answering system cannot solve…

The past thirty years have shown a rise in models of language acquisition in which the state of the learner is characterized as a probability distribution over a set of non-stochastic grammars. In recent years, increasingly powerful models have been constructed as earlier models have failed to generalize well to increasingly complex and realistic…

This study explores using transfer learning in machine learning for natural language processing (NLP) to create generic automated essay scoring (AES) models, providing instant online scoring for statewide writing assessments in K-12 education. The goal is to develop an instant online scorer that is generalizable to any prompt, addressing the…

Data-driven learning uncontroversially plays a role in human language acquisition--how large a role is a matter of much debate. The success of artificial neural networks in NLP in recent years calls for a re-evaluation of our understanding of the possibilities for learning grammar from data alone. This dissertation argues the case for using…

Dialogue act (DA) classification plays an important role in understanding, interpreting and modeling dialogue. Dialogue acts (DAs) represent the intended meaning of an utterance, which is associated with the illocutionary force (or the speaker's intention), such as greetings, questions, requests, statements, and agreements. In natural language…

In light of the ever-increasing capability of computer technology and advancement in speech and natural language processing techniques, automated speech scoring of constructed responses is gaining popularity in many high-stakes assessment and low-stakes educational settings. Automated scoring is a highly interdisciplinary and complex subject, and…

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…

This research aims to discover interpersonal trust in online communities. Two novel trust models are built to explain interpersonal trust in online communities drawing theories and models from multiple relevant areas, including organizational trust models, trust in virtual settings, speech act theory, identity theory, and common bond theory. In…

Open source projects do have requirements; they are, however, mostly informal, text descriptions found in requests, forums, and other correspondence. Understanding such requirements provides insight into the nature of open source projects. Unfortunately, manual analysis of natural language requirements is time-consuming, and for large projects,…

The goal of this dissertation is to determine the best way to train a statistical machine translation system. I first develop a state-of-the-art machine translation system called Phrasal and then use it to examine a wide variety of potential learning algorithms and optimization criteria and arrive at two very surprising results. First, despite the…

This work covers topics in event coreference and event classification from spoken conversation. Event coreference is the process of identifying descriptions of the same event across sentences, documents, or structured databases. Existing event coreference work focuses on sentence similarity models or feature based similarity models requiring slot…

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…

The past two decades have shown an unexpected effectiveness of "Web-scale" data in natural language processing. Even the simplest models, when paired with unprecedented amounts of unstructured and unlabeled Web data, have been shown to outperform sophisticated ones. It has been argued that the effectiveness of Web-scale data has…

This dissertation studies how people describe emotions with language and how computers can simulate this descriptive behavior. Although many non-human animals can express their current emotions as social signals, only humans can communicate about emotions symbolically. This symbolic communication of emotion allows us to talk about emotions that we…