The deep semantic understanding necessary for complex natural language processing tasks, such as automatic question-answering or text summarization, would benefit from highly accurate word sense disambiguation (WSD). This dissertation investigates what makes an appropriate and effective sense inventory for WSD. Drawing on theories and…

One important task of any semantic theory of plurals is to account for the collective/distributive ambiguity. The goal of this dissertation is to achieve greater understanding of plurality and the collectivity/distributivity distinction from a cross-linguistic perspective by examining the phenomenon of distributivity in Mandarin Chinese. I show…

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.…

According to the conjunction rule, the probability of A "and" B cannot exceed the probability of either single event. This rule reads "and" in terms of the logical operator [inverted v], interpreting A and B as an intersection of two events. As linguists have long argued, in natural language "and" can convey a wide range of relationships between…

For over 30 years, reference resolution, the process of determining what a noun phrase including a pronoun refers to in written and spoken language, has been an important and on-going area of research. Most existing pronominal reference resolution algorithms and systems are designed to use syntactic information and surface features (e.g. number…

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…

One of the problems associated with automatic thesaurus construction is with determining the semantic relationship between word pairs. Quasi-synonyms provide a type of equivalence relationship: words are similar only for purposes of information retrieval. Determining such relationships in a thesaurus is hard to achieve automatically. The term…

Web 3.0, termed as the semantic web or the web of data is the transformed version of Web 2.0 with technologies and functionalities such as intelligent collaborative filtering, cloud computing, big data, linked data, openness, interoperability and smart mobility. If Web 2.0 is about social networking and mass collaboration between the creator and…

In this study I introduce BioFrameNet, an extension of the Berkeley FrameNet lexical database to the domain of molecular biology. I examine the syntactic and semantic combinatorial possibilities exhibited in the lexical items used in this domain in order to get a better understanding of the grammatical properties of the language used in scientific…

We explored children's early interpretation of numerals and linguistic number marking, in order to test the hypothesis (e.g., Carey (2004). Bootstrapping and the origin of concepts. "Daedalus", 59-68) that children's initial distinction between "one" and other numerals (i.e., "two," "three," etc.) is bootstrapped from a prior distinction between…

Gradable adjectives denote a function that takes an object and returns a measure of the degree to which the object possesses some gradable property [Kennedy, C. (1999). Projecting the adjective: The syntax and semantics of gradability and comparison. New York: Garland]. Scales, ordered sets of degrees, have begun to be studied systematically in…

Commenting source code has long been a common practice in software development. This thesis, consisting of three pieces of work, made novel use of the code comments written in natural language to improve software reliability. Our solution combines Natural Language Processing (NLP), Machine Learning, Statistics, and Program Analysis techniques to…

Referential identification and resolution are considered the keys to help readers grasp the main idea of a text and solve lexical ambiguities. The goal of this study is to design a computer system for helping college students who learn English as a Foreign Language (EFL) develop mental maps of referential identification and resolution in reading.…

This edited volume provides an overview of the latest advancements in adaptive training technology. Intelligent tutoring has been deployed for well-defined and relatively static educational domains such as algebra and geometry. However, this adaptive approach to computer-based training has yet to come into wider usage for domains that are less…

This article argues that a clear division between two sources of information--one oriented to world knowledge, the other to linguistic semantics--offers a framework within which mechanisms for modelling the highly flexible relation between language and interpretation necessary for natural discourse can be specified and empirically validated.…