Improving Extractive Summaries through Abstractive Transformers

Thumbnail
Name:
azu_etd_20185_sip1_m.pdf
Size:
502.3Kb
Format:
PDF
Download
Author
Kreso, Marko
Issue Date
2022
Keywords
Mixed Abstractive Extractive
Natural Language Processing
NLP
PubMed
Text Summarization
Transformers
Advisor
Surdeanu, Mihai

Metadata
Show full item record
Publisher
The University of Arizona.
Rights
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction, presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract
This paper focuses on using a novel unsupervised summarization layer, called BART-textrank, that uses both abstractive and extractive techniques to produce a final extractive summary. This unsupervised layer is versatile since it can be added on top of any abstractive summarizer without additional training. It is used in conjunction with a base size transformer that achieves SOTA performance in a few metrics when comparing to transformer methods with similar parameter size, and remains competitive with large transformers. The competitiveness of BART-textrank is apparent in figure 4.2.
Type
text
Electronic Thesis
Degree Name
M.S.
Degree Level
masters
Degree Program
Graduate College
Computer Science
Degree Grantor
University of Arizona
Collections