This dissertation focuses on strategies and techniques to enhance code comprehension skills among students enrolled in introductory computer science courses (CS1 and CS2). We propose a novel tutoring system, "DeepCodeTutor," designed to improve the code comprehension abilities of novices. DeepCodeTutor employs scaffolded self-explanation…

Linguistic meaning is generated by the mind and can be expressed in multiple languages. One may assume that equivalent texts/utterances in two languages by means of translation generate equivalent meanings in their readers/hearers. This follows if we assume that meaning calculated from the linguistic input is solely objective in nature. However,…

This dissertation sheds light on some of the representations used in human language production. Language production consists of several distinct stages; in particular, we focus on the stages of lexical retrieval and grammatical encoding. Lexical retrieval involves retrieving the words required to express the intended meaning; grammatical encoding…

The objective of this research is to build automated models that emulate VerbNet, a semantic resource for English verbs. VerbNet has been built and expanded by linguists, forming a hierarchical clustering of verbs with common semantic and syntactic expressions, and is useful in semantic tasks. A major drawback is the difficulty of extending a…

This dissertation represents the first attempt to integrate typological, semantic, and psycholinguistic perspectives to elucidate a semantically "bizarre" and "illogical" phenomenon called "expletive negation" (henceforth, EN) which is well known in Romance languages but has so far attracted little attention outside…

Text classification typically performs best with large training sets, but short texts are very common on the World Wide Web. Can we use resampling and data augmentation to construct larger texts using similar terms? Several current methods exist for working with short text that rely on using external data and contexts, or workarounds. Our focus is…

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…

The World Wide Web enables an easy, instant access to a huge quantity of information. Over the last few decades, a number of improvements have been achieved that helped the web reach its current state. However, the current Internet links documents together without understanding them, and thus, makes the content of web only human-readable rather…

School and university classrooms remain the standard around the world for second language instruction. However, over the past 20 years various methods of language learning have permeated the educational landscape to include self-study textbooks, language learning software and online teachers. Some models are evidence based while others lack…

Information used to assist biomedical and clinical research has largely comprised of data available in published sources like scientific papers and journals, or in clinical sources like patient health records, lab reports and discharge summaries. Information from such sources, though extensive and organized, is often not readily available due to…

This dissertation presents various machine learning applications for predicting different cognitive states of students while they are using a vocabulary tutoring system, DSCoVAR. We conduct four studies, each of which includes a comprehensive analysis of behavioral and linguistic data and provides data-driven evidence for designing personalized…

Compound surnames in Japanese show complex phonological patterns, which pose challenges to current theories of phonology. This dissertation proposes an account of the segmental and prosodic issues in Japanese surnames and discusses their theoretical implications. Like regular compound words, compound surnames may undergo a sound alternation known…

Information sources such as relational databases, spreadsheets, XML, JSON, and Web APIs contain a tremendous amount of structured data, however, they rarely provide a semantic model to describe their contents. Semantic models of data sources capture the intended meaning of data sources by mapping them to the concepts and relationships defined by a…

Bilingual language control refers to how bilinguals are able to speak exclusively in one language without the unintended language intruding. Two prominent verbal theories of bilingual language control have been proposed by researchers: the inhibitory control model (ICM) and the lexical selection mechanism model (LSM). The ICM posits that…

A construction project requires collaboration of different organizations such as owner, designer, contractor, and resource suppliers. These organizations need to exchange information to improve their teamwork. Understanding the information created in other organizations requires specialized human resources. Construction cost estimating is one of…