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 Searching through semantic data using SPARQL requires expert knowledge and thus remains out of reach for casual users. In this work, we explore the development of natural language interfaces for semantic data. This work looks at a number of approaches towards this goal as well as providing a new approach. Our system works like a natural language compiler and handles a limited set of natural language questions which, though narrow in scope, have complex semantics that other systems would...

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...

Abstract Recommending touristic places for visitors is an important service of touristic websites. Most websites allow visitors to either numerically rate or leave a review about the site they visited to express their opinion. Those reviews help future visitors choose the place that is the most attractive to them, and at the same time allow the touristic place owner to improve and increase the visitor's satisfaction. Sometimes, the amount of reviews can be overwhelming, discouraging intended...