A study of text summarization with graph attention networks

Simple item page
dc.contributor.authorArdestani, Mohammadreza
dc.contributor.authorUniversity of Lethbridge. Faculty of Arts and Science
dc.contributor.supervisorChali, Yllias
dc.date.accessioned2024-10-11T20:46:45Z
dc.date.available2024-10-11T20:46:45Z
dc.date.issued2024
dc.degree.levelMasters
dc.description.abstractThis study aimed to leverage graph information, particularly Rhetorical Structure Theory (RST) and Co-reference (Coref) graphs, to enhance the performance of our baseline sum- marization models. Specifically, we experimented with a Graph Attention Network archi- tecture to incorporate graph information. However, this architecture did not enhance the performance. Subsequently, we used a simple Multi-layer Perceptron architecture, which improved the results in our proposed model on our primary dataset, CNN/DM. Addition- ally, we annotated XSum dataset with RST graph information, establishing a benchmark for future graph-based summarizing models. This secondary dataset posed multiple chal- lenges, revealing both the merits and limitations of our models.
dc.embargoNo
dc.identifier.urihttps://hdl.handle.net/10133/6940
dc.language.isoen
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.subjectnatural language processing
dc.subjecttext summarization
dc.subjectgraph attention networks
dc.subjectsummarization models
dc.subjectstage-wise summarization model
dc.subject.lcshDissertations, Academic
dc.subject.lcshComputational linguistics
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshAutomatic abstracting
dc.subject.lcshText processing (Computer science)
dc.subject.lcshElectronic information resources--Abstracting and indexing
dc.titleA study of text summarization with graph attention networks
dc.typeThesis
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
ARDESTANI_MOHAMMADREZA_MSC_2024.pdf
Size:
6.29 MB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
ARDESTANI_MOHAMMADREZA_MSC_THESIS_SUPPLEMENTARY_INFORMATION_2024.pdf
Size:
1.47 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
3.33 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses