Show simple item record

dc.contributor.supervisor Chali, Yllias
dc.contributor.author Nayeem, Mir Tafseer
dc.contributor.author University of Lethbridge. Faculty of Arts and Science
dc.date.accessioned 2017-12-09T23:35:19Z
dc.date.available 2017-12-09T23:35:19Z
dc.date.issued 2017
dc.identifier.uri https://hdl.handle.net/10133/4993
dc.description.abstract In this thesis, we have developed several techniques for tackling both the extractive and abstractive text summarization tasks. We implement a rank based extractive sentence selection algorithm. For ensuring a pure sentence abstraction, we propose several novel sentence abstraction techniques which jointly perform sentence compression, fusion, and paraphrasing at the sentence level. We also model abstractive compression generation as a sequence-to-sequence (seq2seq) problem using an encoder-decoder framework. Furthermore, we applied our sentence abstraction techniques to the multi-document abstractive text summarization. We also propose a greedy sentence ordering algorithm to maintain the summary coherence for increasing the readability. We introduce an optimal solution to the summary length limit problem. Our experiments demonstrate that the methods bring significant improvements over the state-of-the-art methods. At the end of this thesis, we also introduced a new concept called "Reader Aware Summary" which can generate summaries for some critical readers (e.g. Non-Native Reader). en_US
dc.description.sponsorship Natural Sciences and Engineering Research Council (NSERC) of Canada and the University of Lethbridge en_US
dc.language.iso en_US en_US
dc.publisher Lethbridge, Alta. : Universtiy of Lethbridge, Department of Mathematics and Computer Science en_US
dc.relation.ispartofseries Thesis (University of Lethbridge. Faculty of Arts and Science) en_US
dc.subject automatic text summarization en_US
dc.subject multi-document text summarization en_US
dc.subject neural paraphrastic compression en_US
dc.subject sentence abstraction en_US
dc.subject sequence-to-sequence en_US
dc.title Methods of sentence extraction, abstraction and ordering for automatic text summarization en_US
dc.type Thesis en_US
dc.publisher.faculty Arts and Science en_US
dc.publisher.department Department of Mathematics and Computer Science en_US
dc.degree.level Masters en_US
dc.proquest.subject 0723 en_US
dc.proquest.subject 0800 en_US
dc.proquest.subject 0984 en_US
dc.proquestyes Yes en_US
dc.embargo No en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record