{"id":{"repo_id":"umn","oai_identifier":"oai:conservancy.umn.edu:11299/216372"},"canonical_url":"https://search.dev.ndltd.org/etd/umn/oai:conservancy.umn.edu:11299/216372","repository":{"repo_id":"umn","name":"University of Minnesota","base_url":"https://conservancy.umn.edu/server/oai/request"},"display":{"title":"Multiple Choice Question Answering using a Large Corpus of Information","abstract":"The amount of natural language data is massive and the potential to harness the information contained within has led to many recent discoveries. In this dissertation I explore only one aspect of learning with the goal of answering multiple choice questions with information from a large corpus of information. I chose this topic because of an internship at NASA’s Jet Propulsion Laboratory, where there is a growing interest in making rovers more autonomous in their field research. Being able to process information and act correctly is a key stepping stone to accomplish this, which is an aspect my dissertation covers. The chapters involve a review on the early embedding methods, and two novel approaches to create multiple choice question answering mechanisms. In Chapter 2 I review popular algorithms to create word and sentence embeddings given the surrounding context. These embeddings are a numerical representation of the language data that can be used in downhill models such as logistic regression. In Chapter 3 I present a novel method to create a domain specific knowledge base that can be querired to answer multiple choice questions from a database of Elementary School science questions. The knowledge base is made up of a graph structure and trained using deep learning techniques. The classifier creates an embedding to represent the question and answers. This embedding is then passed through a feed forward network to determine the probability of a correct answer. We train on questions and general information from a large corpus in a semi-supervised setting. In Chapter 4 I propose a strategy to train a network to simultaneously classify multiple choice questions and learn to generate words relevant to the surrounding context of the question. Using the Transformer architecture in a Generative Adversarial Network as well as an additional classifier is a novel approach to train a network that is robust against data not seen in the training set. This semi-supervised training regiment also uses sentences from a large corpus of information and Reinforcement Learning to better inform the generator of relevant words","abstract_html":"The amount of natural language data is massive and the potential to harness the information contained within has led to many recent discoveries. In this dissertation I explore only one aspect of learning with the goal of answering multiple choice questions with information from a large corpus of information. I chose this topic because of an internship at NASA’s Jet Propulsion Laboratory, where there is a growing interest in making rovers more autonomous in their field research. Being able to process information and act correctly is a key stepping stone to accomplish this, which is an aspect my dissertation covers. The chapters involve a review on the early embedding methods, and two novel approaches to create multiple choice question answering mechanisms. In Chapter 2 I review popular algorithms to create word and sentence embeddings given the surrounding context. These embeddings are a numerical representation of the language data that can be used in downhill models such as logistic regression. In Chapter 3 I present a novel method to create a domain specific knowledge base that can be querired to answer multiple choice questions from a database of Elementary School science questions. The knowledge base is made up of a graph structure and trained using deep learning techniques. The classifier creates an embedding to represent the question and answers. This embedding is then passed through a feed forward network to determine the probability of a correct answer. We train on questions and general information from a large corpus in a semi-supervised setting. In Chapter 4 I propose a strategy to train a network to simultaneously classify multiple choice questions and learn to generate words relevant to the surrounding context of the question. Using the Transformer architecture in a Generative Adversarial Network as well as an additional classifier is a novel approach to train a network that is robust against data not seen in the training set. This semi-supervised training regiment also uses sentences from a large corpus of information and Reinforcement Learning to better inform the generator of relevant words","abstract_has_math":false,"creators":["Kinney, Mitchell"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-07","date_published":"2020-07","updated_at":"2026-07-24T05:19:58Z","subjects":["Embeddings","Generative Adversarial Network","Graph Neural Network","Reinforcement Learning"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11299/216372","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Kinney, Mitchell"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-09-22T21:02:38Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-09-22T21:02:38Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-07"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Embeddings","Generative Adversarial Network","Graph Neural Network","Reinforcement Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11299/216372"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["University of Minnesota Ph.D. dissertation. July 2020. Major: Statistics. Advisor: Xiaotong Shen. 1 computer file (PDF); vii, 199 pages."]},{"key":"dc:description.abstract","label":"Abstract","values":["The amount of natural language data is massive and the potential to harness the information contained within has led to many recent discoveries. In this dissertation I explore only one aspect of learning with the goal of answering multiple choice questions with information from a large corpus of information. I chose this topic because of an internship at NASA’s Jet Propulsion Laboratory, where there is a growing interest in making rovers more autonomous in their field research. Being able to process information and act correctly is a key stepping stone to accomplish this, which is an aspect my dissertation covers. The chapters involve a review on the early embedding methods, and two novel approaches to create multiple choice question answering mechanisms. In Chapter 2 I review popular algorithms to create word and sentence embeddings given the surrounding context. These embeddings are a numerical representation of the language data that can be used in downhill models such as logistic regression. In Chapter 3 I present a novel method to create a domain specific knowledge base that can be querired to answer multiple choice questions from a database of Elementary School science questions. The knowledge base is made up of a graph structure and trained using deep learning techniques. The classifier creates an embedding to represent the question and answers. This embedding is then passed through a feed forward network to determine the probability of a correct answer. We train on questions and general information from a large corpus in a semi-supervised setting. In Chapter 4 I propose a strategy to train a network to simultaneously classify multiple choice questions and learn to generate words relevant to the surrounding context of the question. Using the Transformer architecture in a Generative Adversarial Network as well as an additional classifier is a novel approach to train a network that is robust against data not seen in the training set. This semi-supervised training regiment also uses sentences from a large corpus of information and Reinforcement Learning to better inform the generator of relevant words"]},{"key":"dc:title","label":"Title","values":["Multiple Choice Question Answering using a Large Corpus of Information"]}]}],"canonical_facts":{"dc:creator":["Kinney, Mitchell"],"dc:date.accessioned":["2020-09-22T21:02:38Z"],"dc:date.available":["2020-09-22T21:02:38Z"],"dc:date.issued":["2020-07"],"dc:description":["University of Minnesota Ph.D. dissertation. July 2020. Major: Statistics. Advisor: Xiaotong Shen. 1 computer file (PDF); vii, 199 pages."],"dc:description.abstract":["The amount of natural language data is massive and the potential to harness the information contained within has led to many recent discoveries. In this dissertation I explore only one aspect of learning with the goal of answering multiple choice questions with information from a large corpus of information. I chose this topic because of an internship at NASA’s Jet Propulsion Laboratory, where there is a growing interest in making rovers more autonomous in their field research. Being able to process information and act correctly is a key stepping stone to accomplish this, which is an aspect my dissertation covers. The chapters involve a review on the early embedding methods, and two novel approaches to create multiple choice question answering mechanisms. In Chapter 2 I review popular algorithms to create word and sentence embeddings given the surrounding context. These embeddings are a numerical representation of the language data that can be used in downhill models such as logistic regression. In Chapter 3 I present a novel method to create a domain specific knowledge base that can be querired to answer multiple choice questions from a database of Elementary School science questions. The knowledge base is made up of a graph structure and trained using deep learning techniques. The classifier creates an embedding to represent the question and answers. This embedding is then passed through a feed forward network to determine the probability of a correct answer. We train on questions and general information from a large corpus in a semi-supervised setting. In Chapter 4 I propose a strategy to train a network to simultaneously classify multiple choice questions and learn to generate words relevant to the surrounding context of the question. Using the Transformer architecture in a Generative Adversarial Network as well as an additional classifier is a novel approach to train a network that is robust against data not seen in the training set. This semi-supervised training regiment also uses sentences from a large corpus of information and Reinforcement Learning to better inform the generator of relevant words"],"dc:identifier.uri":["http://hdl.handle.net/11299/216372"],"dc:language.iso":["en"],"dc:subject":["Embeddings","Generative Adversarial Network","Graph Neural Network","Reinforcement Learning"],"dc:title":["Multiple Choice Question Answering using a Large Corpus of Information"],"dc:type":["Thesis or Dissertation"]},"updated_at":"2026-07-24T05:19:58Z"}