Date Available
4-9-2022
Year of Publication
2022
Degree Name
Doctor of Philosophy (PhD)
Document Type
Doctoral Dissertation
College
Engineering
Department/School/Program
Computer Science
First Advisor
Dr. Brent Harrison
Abstract
As AI and machine learning systems become more common in our everyday lives, there is an increased desire to construct systems that are able to seamlessly interact and communicate with humans. This typically means creating systems that are able to communicate with humans via natural language. Given the variance of natural language, this can be a very challenging task. In this thesis, I explored the topic of humanlike language generation in the context of stylized language generation. Stylized language generation involves producing some text that exhibits a specific, desired style. In this dissertation, I specifically explored the use of multi-modality features as a means to provide sufficient information to produce high-quality stylized text output. I also explored how these multi-modality features can be used to identify and explain errors in the generated output. Finally, I constructed an automated language evaluation metric that can evaluate stylized language models.
Digital Object Identifier (DOI)
https://doi.org/10.13023/etd.2022.054
Recommended Citation
Li, Chengxi, "Supporting Stylized Language Models Using Multi-Modality Features" (2022). Theses and Dissertations--Computer Science. 115.
https://uknowledge.uky.edu/cs_etds/115
