Publication Date


Document Type


Committee Members

Nikolaos Bourbakis (Advisor), Soon Chung (Committee Member), Arnab K. Shaw (Committee Member), Michael Talbert (Committee Member), Krishnaprasad Thirunarayan (Committee Member)

Degree Name

Doctor of Philosophy (PhD)


The purpose of this research is to design and implement a new methodology that captures the natural language understanding of events from English natural language text and model it using Stochastic Petri Nets. To establish a baseline of recent natural language processing (NLP) and understanding (NLU) research, two surveys are presented. One is a general survey in NLP and NLU methodologies for processing multi-documents. It summarizes and presents methodologies in terms of their features, capabilities, and maturity. The second survey focuses on graph-based methods for NL text processing and understanding and analyzes them in terms of their functional descriptions, capabilities and maturities. In recent years, NLP/NLU researchers have narrowed their domain to graph methodologies due to improved efficiency over older methods. Thus, to accomplish our goal, we firstly implemented a NL text to graph conversion method. This method extracts events in terms of their agents, actions, and patients from subject nouns, verbs, and object nouns within each phrase and sentence of a text and produces a graph consisting of nodes representing nouns and verbs and edges representing their relations. A significant effort went into handling complex sentences consisting of multiple phrases, active and passive sentences, and multiple agents, actions, and patients. The graph provides a baseline implementation, which we could relate to other graph methodologies and provide a structured approach to NLP and NLU from text. Next, we embedded a new NL text-graphs to Stochastic Petri Net (SPN) graph conversion methodology into our model to represent events associated with NL text. SPN graphs provide not only a structured representation that graphs provide, but also other capabilities, such as representing and adjusting timing using its transition components, constraining flow with its inhibiting places, stochastic behavior of its markings, and color markings [89, 90]. We use these added capabilities from SPN modeling to capture new NLU capabilities of events from NL text. We demonstrated sentence disambiguation of events.

Page Count


Department or Program

Department of Computer Science and Engineering

Year Degree Awarded


Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.