Query focused abstractive summarization using BERTSUM model

Simple item page
dc.contributor.authorAbdullah, Deen Mohammad
dc.contributor.authorUniversity of Lethbridge. Faculty of Arts and Science
dc.contributor.supervisorChali, Yllias
dc.date.accessioned2020-09-09T19:52:57Z
dc.date.available2020-09-09T19:52:57Z
dc.date.issued2020
dc.degree.levelMastersen_US
dc.description.abstractIn Natural Language Processing, researchers find many challenges on Query Focused Abstractive Summarization (QFAS), where Bidirectional Encoder Representations from Transformers for Summarization (BERTSUM) can be used for both extractive and abstractive summarization. As there is few available datasets for QFAS, we have generated queries for two publicly available datasets, CNN/Daily Mail and Newsroom, according to the context of the documents and summaries. To generate abstractive summaries, we have applied two different approaches, which are Query focused Abstractive and Query focused Extractive then Abstractive summarizations. In the first approach, we have sorted the sentences of the documents from the most query-related sentences to the less query-related sentences, and in the second approach, we have extracted only the query related sentences to fine-tune the BERTSUM model. Our experimental results show that both of our approaches show good results on ROUGE metric for CNN/Daily Mail and Newsroom datasets.en_US
dc.identifier.urihttps://hdl.handle.net/10133/5760
dc.language.isoen_USen_US
dc.proquest.subject0537en_US
dc.proquest.subjectComputer science [0984]en_US
dc.proquest.subjectArtificial intelligence [0800]en_US
dc.proquest.subjectEngineering [0537]en_US
dc.proquestyesYesen_US
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Scienceen_US
dc.publisher.departmentDepartment of Mathematics and Computer Scienceen_US
dc.publisher.facultyArts and Scienceen_US
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)en_US
dc.subjectNatural language processingen_US
dc.subjectNatural language generation (Computer science)en_US
dc.subjectText data miningen_US
dc.subjectSoftware engineeringen_US
dc.subjectSystems engineeringen_US
dc.subjectDissertations, Academic
dc.titleQuery focused abstractive summarization using BERTSUM modelen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ABDULLAH_DEEN_MOHAMMAD_MSC_2020.pdf
Size:
1.67 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