Abstractive text summarization based on neural fusion

Simple item page
dc.contributor.authorZhu, Wenzhao
dc.contributor.authorUniversity of Lethbride. Faculty of Arts and Science
dc.contributor.supervisorChali, Yllias
dc.date.accessioned2024-01-24T19:31:12Z
dc.date.available2024-01-24T19:31:12Z
dc.date.issued2023
dc.degree.levelMasters
dc.description.abstractAbstractive text summarization, in comparison to extractive text summarization, offers the potential to generate more accurate summaries. In our work, we present a stage-wise abstractive text summarization model that incorporates Elementary Discourse Unit (EDU) segmentation, EDU selection, and EDU fusion. We first segment the articles into a fine-grained form, EDUs, and build a Rhetorical Structure Theory (RST) tree for each article in order to represent the dependencies among EDUs; those EDUs are encoded in Graph Attention Networks (GATs); those with higher importance will be selected as candidates to be fused and the fusing stage is done by Bidirectional and Auto-Regressive Transformers (BART) model which merges the selected EDUs into summaries. A Greedy Method is leveraged to greedily select those EDUs whose combinations can maximize the ROUGE scores. Our model outperforms the baseline of BART (large) on the CNN/Daily Mail dataset, showing its effectiveness in abstractive text summarization.
dc.identifier.urihttps://hdl.handle.net/10133/6669
dc.language.isoen
dc.proquest.subject0800
dc.proquest.subject0984
dc.proquestyesYes
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science
dc.publisher.departmentDepartment of Mathematics and Computer Science
dc.publisher.facultyArts and Science
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)
dc.subjectAbstractive text summarization
dc.subjectElementary discourse unit
dc.subjectRhetorical structure theory
dc.subjectNeural networks
dc.subjectNeural fusion
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshDissertations, Academic
dc.titleAbstractive text summarization based on neural fusion
dc.typeThesis
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
WENZHAO_ZHU_MSC_2023.pdf
Size:
1.98 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
3.25 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses