Variability is intrinsic to human speech production. One approach to understand variability in speech is to decompose it into task-irrelevant ("good") and task-relevant ("bad") parts with respect to speech tasks. Based on the uncontrolled manifold (UCM) approach, this dissertation investigates how vowel token-to-token…

The exponential growth of digital libraries and the proliferation of scholarly content in electronic formats have made data mining and information retrieval essential tools for effectively managing, organizing, and disseminating knowledge. This thesis provides a comprehensive analysis of the advancements and challenges in these fields, with a…

Bag-of-words is a commonly used text representation method for many text classification applications. However, bag-of-words representation fails to consider the context of the text because it only examines text documents based on the presence of individual words and explores relationships between texts with similar word choices (Bengfort, 2018).…

This dissertation studies the acquisition of Mandarin relative clauses (RCs), including the distributional pattern of different RC types in adult child-directed speech (study 1) and four-year-old Mandarin-speaking children's comprehension of different RC types (study 2). An RC is a subordinate clause that modifies a noun and is embedded within a…

This study employs a relational database consisting of thousands of Old High German (OHG) nominal attestations to reconstruct noun class paradigms found primarily in the four OHG texts extensive enough to provide complete nominal paradigms: "Isidor", "Benediktinerregel", "Tatian" and Otfrid von Weissenburg's "Evangelienbuch". This study captures…

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…

The variety and complexity of potentially-related data resources available for querying--webpages, databases, data warehouses--has been growing ever more rapidly. There is a growing need to pose integrative queries "across" multiple such sources, exploiting foreign keys and other means of interlinking data to merge information from diverse…

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…

The present study is based on the theoretical assumptions that frequency of characters and their structural components, as well as the frequency types of structural components, are important to enable learners of Chinese as a foreign language (CFL) to discover the underlying structure of Chinese characters. In the CFL context, since reliable…