Computer Science ETDs
Publication Date
Summer 5-7-2021
Abstract
Question answering systems are models that can perform natural language processing (NLP) on a question, retrieve an answer from a datasource, and communicate it to a user. In question answering systems, it is important for the system to learn an underlying representation for a piece of text. There are many systems that have achieved incredible accuracy on question answering datasets such as the Stanford Question and Answer Dataset (SQuAD), but these systems often encode their knowledge in a manner that is impossible to verify. Many current models would benefit more from verifiability, than marginal accuracy improvements.
We propose a method to learn representations for a piece of text in a manner that is human-auditable. The model accomplishes these goals by leveraging the power of modern transformer neural network models and a unique dataset to create a model that is accurate and interpretable.
Language
English
Keywords
natural language processing, transformers, NLP, intermediate representations
Document Type
Thesis
Degree Name
Computer Science
Level of Degree
Masters
Department Name
Department of Computer Science
First Committee Member (Chair)
Lydia Tapia
Second Committee Member
George Luger
Third Committee Member
Leah Buechley
Recommended Citation
Clarke, Zakery T.. "Learning Intermediate Representations for Question Answering Systems." (2021). https://digitalrepository.unm.edu/cs_etds/109
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons
