Michael Raymer, Ph.D. (Advisor); Mateen Rizki, Ph.D. (Committee Member); Krishnaprasad Thirunarayan, Ph.D. (Committee Member)
Master of Science (MS)
Sentence embeddings are frequently generated by using complex, pretrained models that were trained on a very general corpus of data. This thesis explores a potential alternative method for generating high-quality sentence embeddings for highly specialized corpora in an efficient manner. A framework for visualizing and analyzing sentence embeddings is developed to help assess the quality of sentence embeddings for a highly specialized corpus of documents related to the 2019 coronavirus epidemic. A Topological Data Analysis (TDA) technique is explored as an alternative method for grouping embeddings for document clustering and topic modeling tasks and is compared to a simple clustering method for effectiveness. The sentence embeddings generated are found to be effective for use in similarity based tasks and group in useful ways when used with the TDA based techniques explored as alternatives to traditional clustering-based approaches.
Department or Program
Department of Computer Science and Engineering
Year Degree Awarded
Copyright 2020, all rights reserved. My ETD will be available under the "Fair Use" terms of copyright law.