Abstract There exist numerous methods and a plethora of languages for controlling software and physical agents. This is a very important endeavor because by using intelligent agents, it could potentially free humans from boring, repetitive tasks, or from dangerous activities. Coupled with this, is one of the most significant goals in Computer Science: the creation of autonomous, intelligent agents. This implies that the intelligent agents possess some potential for learning. The learning...

Abstract Bidirectional Encoder Representations from Transformers (BERT), introduced by Google, is a powerful natural language processing model as it is able to understand the meaning of words in a sentence in context. WordNet, developed at Princeton University, is a lexical database that shows semantic relationships between words. This thesis looks to investigate BERT’s word categorization system by looking at groups of example sentences given from related WordNet synsets. Because BERT allows a...

Abstract The goal of this research is to evaluate the usefulness of enhanced named entity recognition for text mining. Text mining is a subpart of data mining. It is the application of data mining techniques to texts in natural language such as English. The data for this project consists news [sic] articles and article titles extracted from the Web. Enhanced name-entity recognition is used to add additional information to the text. Named entities in the text are...