The objective of question generation from knowledge graphs (KGQG) is to create coherent and answerable questions from a given subgraph and a specified answer entity. KGQG has garnered significant attention due to its pivotal role in enhancing online education. Encoder-decoder architectures have advanced traditional KGQG approaches. However, these…

Reading comprehension is key to knowledge acquisition and to reinforcing memory for previous information. While reading, a mental representation is constructed in the reader's mind. The mental model comprises the words in the text, the relations between the words, and inferences linking to concepts in prior knowledge. The automated model of…

Academic grades in assessments are predicted to determine if a student is at risk of failing a course. Sequential models or graph neural networks that have been employed for grade prediction do not consider relationships between course descriptions. We propose the use of text mining to extract semantic, syntactic, and frequency-based features from…

The "syntactic bootstrapping" hypothesis proposes that syntactic structure provides children with cues for learning the meaning of novel words. In this article, we address the question of how children might start acquiring some aspects of syntax before they possess a sizeable lexicon. The study presents two models of early syntax…

Much recent work in natural language processing treats linguistic analysis as an inference problem over graphs. This development opens up useful connections between machine learning, graph theory, and linguistics. The first part of this dissertation formulates syntactic dependency parsing as a dynamic Markov random field with the novel…

The usage and disappearance of the Central Ibero-Romance future subjunctive have been extensively researched through Old Spanish texts. Studies on the future subjunctive as it evolved in the farther Western Ibero-Romance languages, represented by Galician and Portuguese, have been scarce, if not incomplete. This dissertation partially fills the…

Argues that tables, graphs, and diagrams extend language's power by exploiting the Euclidean possibilities which a text suggests. Notes that graphic display elements form no compatible natural set and that their value and visual elements are decisively disparate. Concludes that graphic displays are unlikely candidates for unitary theoretical…

A discussion of autosegmental phonology (AP), a theory of phonological representation that uses graphs rather than strings as the central data structure, considers its principal constraint, the "No Crossing Constraint" (NCC). The NCC is the statement that in a well-formed autosegmental diagram, lines of association may not cross. After…

The technique developed in this research paper for analyzing the information in charts and graphs is designed to reveal design flaws in the display that may prevent them from conveying information effectively. This analytic scheme requires isolating four types of constituents in a display and specifying their structure and interrelations at the…

Presents an analysis of errors in a 400-page corpus of German essays by American college students in second-year language courses showing that syntax is the most problematic area, followed by morphology. This study indicates that 80% of student errors are not of semantic origin and are potentially recognizable by a syntactic parser. (six…