Date of Award
Master of Science (MS)
Dr. Laura Grabowski
Dr. Emmett Tomai
Dr. Zhixiang Chen
In this paper I will analyze three different algorithms and approaches to implement Question Answering Systems (QA-Systems). I will analyze the efficiency, strengths, and weaknesses of multiple algorithms by explaining them in detail and comparing them with each other. The overarching aim of this thesis is to explore ideas that can be used to create a truly open context QA-System. Open context QA-Systems remain an open problem.
The various algorithms and approaches presented in this work will be focused on complex questions. Complex questions are usually verbose and the context of the question is equally important to answer the query as is the question itself. Such questions represent an interesting problem in the field because they can be answered and written in a number of distinct ways. Also, the answer structure is not always the same and the QA-System needs to compensate for this. The analysis of complex questions differ between contexts. Contexts are the topic to which a complex question belongs, e.g. Biology, literature, etc… The analysis of the answer also differs according to the corpus used. Corpus is a set of documents, belonging to a specific context, where we can find the answer to a specified question. I will start by explaining various algorithms and approaches. I will then analyze its different parts. Finally, I will present some ideas on how to implement QA-Systems.
Balandrano Coronel, Josue, "A comparative approach to Question Answering Systems" (2016). Theses and Dissertations - UTRGV. 8.