Date of Award
Spring 6-8-2020
Degree Type
Thesis
Degree Name
Master of Science (MS)
School
School of Computing
First Advisor
Raffaella Settimi, PhD
Second Advisor
John Shanahan, PhD
Third Advisor
Jon Gemmell, PhD
Fourth Advisor
Tokunbo Hiamang
Abstract
The primary objective of this thesis is to develop a method that uses machine learning algorithms to enable computational story understanding. This research is conducted with the aim of establishing a system called the Native Storyteller that plans and creates storytelling experiences for human users. The paper first establishes the desired capabilities of the system and then deep dives into how to enable story understanding, which is the core ability the system needs to function. As such, the research places emphasis on natural language processing and its application to solving key problems in this context. Namely, machine representation of story data in a way that adequately respects the contextual information in the story; and, identification of relationships between multiple stories based on this contextual knowledge. To do this, the BookNLP pipeline is used as a backbone for extracting structured data from textual stories sourced from My Book of Bible Stories. The core contribution of this work is the application of extensions beyond the BookNLP pipeline through NLP algorithms and ELMo neural language embeddings to create features that represent the system’s computational understanding of its stories, both at a plot and character-level.
Recommended Citation
Kehinde, Aramide O., "Pathways to the Native Storyteller: a method to enable computational story understanding" (2020). College of Computing and Digital Media Dissertations. 22.
https://via.library.depaul.edu/cdm_etd/22