Generative Models for Domain-Specific Summarization
Name
queipo-lqueipom-meng-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
3.09 MB
Format
Adobe PDF
Checksum (MD5)
7143a1d4c42435e50b914d018d031eeb
Author(s)
Queipo, Laura
Advisor(s)
Katz, Boris
Date Issued
September 2023
Publisher
Massachusetts Institute of Technology
Abstract
This project evaluates the performance of generative models of summarization in aviation safety domain. Models such as DaVinci, Text-DaVinci-003, and GPT-3.5-Turbo were analyzed in both their zero-shot learning and fine-tuned performance against state-of-the-art models. In zero-shot learning, generative models were superior in most cases to the state-of-the- art models, whereas the fine-tuned models could learn with less information about the dataset. These results predict promising advances in the summarization space to address current limitations in the field.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
