{"id":{"repo_id":"lethbridge","oai_identifier":"oai:opus.uleth.ca:10133/6669"},"canonical_url":"https://search.dev.ndltd.org/etd/lethbridge/oai:opus.uleth.ca:10133/6669","repository":{"repo_id":"lethbridge","name":"University of Lethbridge","base_url":"https://opus.uleth.ca/server/oai/request"},"display":{"title":"Abstractive text summarization based on neural fusion","abstract":"Abstractive 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.","abstract_html":"Abstractive 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.","abstract_has_math":false,"creators":["Zhu, Wenzhao","University of Lethbride. Faculty of Arts and Science"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-07-27T20:02:41Z","subjects":["Abstractive text summarization","Elementary discourse unit","Rhetorical structure theory","Neural networks","Neural fusion"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["hdl:10133/6669"],"render_values":[{"text":"hdl:10133/6669","href":null,"code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Abstractive text summarization","Elementary discourse unit","Rhetorical structure theory","Neural networks","Neural fusion"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["hdl:10133/6669"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.other","label":"Dc Description Other","values":["Abstractive 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."]},{"key":"dc:title","label":"Title","values":["Abstractive text summarization based on neural fusion"]}]}],"canonical_facts":{"dc:date.issued":["2023"],"dc:description.other":["Abstractive 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":["hdl:10133/6669"],"dc:subject":["Abstractive text summarization","Elementary discourse unit","Rhetorical structure theory","Neural networks","Neural fusion"],"dc:title":["Abstractive text summarization based on neural fusion"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:02:41Z"}