Back to search

Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science

Improving faithfulness in abstractive text summarization with EDUs using BART

Abstract

dc:description.abstract

Abstractive summarization aims to reproduce the essential information of a source document in a summary by using the summarizer's own words. Although this approach is more similar to how humans summarize, it is more challenging to automate as it requires a complete understanding of natural language. However, the development of deep learning approaches, such as the sequence-to-sequence model with an attention-based mechanism, and the availability of pre-trained language models have led to improved performance in summarization systems. Nonetheless, abstractive summarization still suffers from issues such as hallucination and unfaithfulness. To address these issues, we propose an approach that utilizes a guidance signal using important Elementary Discourse Units (EDUs). We compare our work with previous guided summarization and two other summarization models that enhanced the faithfulness of the summary. Our approach was tested on CNN/Daily Mail dataset, and results showed an improvement in both truthfulness and good quantity coverage of the source document.

Degree

thesis:*
Level thesis:degree_level
Masters
Grantor dc:publisher
Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Delpisheh, Narjes
  • University of Lethbridge. Faculty of Arts and Science
Advisor dc:contributor.supervisor
  • Chali, Yllias

Subjects

dc:subject × 11

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/10133/6499

Chain of custody

source
Harvested from
University of Lethbridge
Base URL
opus.uleth.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Delpisheh, Narjes; University of Lethbridge. Faculty of Arts and Science. Improving faithfulness in abstractive text summarization with EDUs using BART. Masters thesis, Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science, 2023. https://hdl.handle.net/10133/6499