Show simple item record

dc.contributor.supervisor Chali, Yllias
dc.contributor.author Egonmwan, Elozino Ofualagba
dc.contributor.author University of Lethbridge. Faculty of Arts and Science
dc.date.accessioned 2021-01-15T17:33:03Z
dc.date.available 2021-01-15T17:33:03Z
dc.date.issued 2020
dc.identifier.uri https://hdl.handle.net/10133/5827
dc.description.abstract This thesis presents studies in neural text summarization for single and multiple documents.The focus is on using sentence paraphrasing and compression for generating fluent summaries, especially in multi-document summarization where there is data paucity. A novel solution is to use transfer-learning from downstream tasks with an abundance of data. For this purpose, we pre-train three models for each of extractive summarization, paraphrase generation and sentence compression. We find that summarization datasets – CNN/DM and NEWSROOM – contain a number of noisy samples. Hence, we present a method for automatically filtering out this noise. We combine the representational power of the GRU-RNN and TRANSFORMER encoders in our paraphrase generation model. In training our sentence compression model, we investigate the impact of using different early-stopping criteria, such as embedding-based cosine similarity and F1. We utilize the pre-trained models (ours, GPT2 and T5) in different settings for single and multi-document summarization. en_US
dc.description.sponsorship SGS Tuition Award Alberta Innovates Technology Futures (AITF) en_US
dc.language.iso en_US en_US
dc.publisher Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science en_US
dc.relation.ispartofseries Thesis (University of Lethbridge. Faculty of Arts and Science) en_US
dc.subject Artificial intelligence en_US
dc.subject Automatic programming (Computer science) en_US
dc.subject Computer programming en_US
dc.subject Dissertations, Academic en_US
dc.subject Machine learning en_US
dc.subject Natural language processing (Computer science) en_US
dc.subject Neural networks (Computer science) en_US
dc.title Abstractive multi-document summarization - paraphrasing and compressing with neural networks 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 Ph.D en_US
dc.proquest.subject Computer science [0984] en_US
dc.proquest.subject Computer engineering [0464] en_US
dc.proquest.subject Artificial intelligence [0800] en_US
dc.proquestyes Yes en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record