This dissertation advances research on evaluation (RoE) through a trio of studies focusing on the role of context and the innovative use of Linguistic Inquiry and Word Count (LIWC) software in formative evaluation in a qualitative research project. The first article extends Coryn et al. (2017) and elucidates how various contextual…

Decades of psycholinguistics research have shown that human sentence processing is highly incremental and predictive. This has provided evidence for expectation-based theories of sentence processing, which posit that the processing difficulty of linguistic material is modulated by its probability in context. However, these theories do not make…

Language is one of the hallmarks of intelligence, demanding explanation in a theory of human cognition. However, language presents unique practical challenges for quantitative empirical research, making many linguistic theories difficult to test at naturalistic scales. Artificial neural network language models (LMs) provide a new tool for studying…

While large language models (LLMs) continue to grow in scale and gain new zero-shot capabilities, their performance for languages beyond English increasingly lags behind. This gap is due to the "curse of multilinguality," where multilingual language models perform worse on individual languages than a monolingual model trained on that…

The essence of human intelligence lies in its ability to learn continuously, accumulating past knowledge to aid in future learning and problem-solving endeavors. In contrast, the current machine learning paradigm often operates in isolation, lacking the capacity for continual learning and adaptation. This deficiency becomes apparent in the face of…

This dissertation investigates how bilinguals use their two grammars to comprehend written intra-sentential codeswitches. I focus on adjective/noun constructions in Spanish and English where I manipulate the congruence of grammatical word order in the two languages across the codeswitch boundary. This allows me to test three codeswitching…

The rapid advancement of powerful Large Language Models (LLMs), such as ChatGPT and Llama, has revolutionized the world by bringing new creative possibilities and enhancing productivity. However, these advancements also pose significant challenges and risks, including the potential for misuse in the form of fake news, academic dishonesty,…

We study how to automatically generate cloze questions from given texts to assess reading comprehension, where a cloze question consists of a stem with a blank space holder for the answer key, and three distractors for generating confusions. We present a generative method called CQG (Cloze Question Generator) for constructing cloze questions from…

This dissertation is an inquiry into the history of Chinese computer-based word processing technologies from 1958 to 1997. My purpose in looking into the history is to answer, how the development and usage of word-processing technologies have contributed to knowledge production, by shaping the understanding of what information technologies can do.…

Throughout history, artificial intelligence (AI) has impacted various aspects of human life and professional industries, including the field of education, by mimicking human behaviors and tasks to increase productivity and efficiency (Grudin et al., 2023; Haenlein & Kaplan, 2019). Generative AI is a form of AI using deep learning to quickly…

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…

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…

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…

Second language learners constitute a significant and expanding portion of the global population and there is a growing demand for tools that facilitate language learning and instruction across various levels and in different countries. The development of large language models (LLMs) has brought about a significant impact on the domains of natural…

Reading comprehension can be analyzed from three points of view: Semantics, Assessment, and Cognition. Here, Semantics refers to the task of identifying discourse relations in text. Assessment involves utilizing these relations to obtain meaningful question-answer pairs. Cognition means categorizing questions according to their difficulty or…