Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units

Abstractive text summarization uses the summarizer's own words to capture the main information of a source document in a summary. While it is more challenging to automate than extractive text summarization, recent advancements in deep learning approaches and pre-trained language models have im...

Full description

Saved in:
Bibliographic Details
Main Authors: Narjes Delpisheh, Yllias Chali
Format: Article
Language:English
Published: LibraryPress@UF 2025-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Online Access:https://journals.flvc.org/FLAIRS/article/view/138888
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725498413809664
author Narjes Delpisheh
Yllias Chali
author_facet Narjes Delpisheh
Yllias Chali
author_sort Narjes Delpisheh
collection DOAJ
description Abstractive text summarization uses the summarizer's own words to capture the main information of a source document in a summary. While it is more challenging to automate than extractive text summarization, recent advancements in deep learning approaches and pre-trained language models have improved its performance. However, abstractive text summarization still has issues such as hallucination and unfaithfulness. To address these problems, we propose a new approach that utilizes important Elementary Discourse Units (EDUs) to guide BART-based text summarization. We compare our approach with some previous approaches that have improved the faithfulness of the summary. Our approach was compared and tested on the CNN/Daily Mail dataset and showed an improvement in truthfulness and source document coverage.  
format Article
id doaj-art-c947e7d01b0e428b964642efcd5489e7
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2025-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-c947e7d01b0e428b964642efcd5489e72025-08-20T03:10:27ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622025-05-0138110.32473/flairs.38.1.138888Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse UnitsNarjes DelpishehYllias Chali0University of Lethbridge Abstractive text summarization uses the summarizer's own words to capture the main information of a source document in a summary. While it is more challenging to automate than extractive text summarization, recent advancements in deep learning approaches and pre-trained language models have improved its performance. However, abstractive text summarization still has issues such as hallucination and unfaithfulness. To address these problems, we propose a new approach that utilizes important Elementary Discourse Units (EDUs) to guide BART-based text summarization. We compare our approach with some previous approaches that have improved the faithfulness of the summary. Our approach was compared and tested on the CNN/Daily Mail dataset and showed an improvement in truthfulness and source document coverage.   https://journals.flvc.org/FLAIRS/article/view/138888
spellingShingle Narjes Delpisheh
Yllias Chali
Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units
Proceedings of the International Florida Artificial Intelligence Research Society Conference
title Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units
title_full Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units
title_fullStr Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units
title_full_unstemmed Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units
title_short Leveraging Faithfulness in Abstractive Text Summarization with Elementary Discourse Units
title_sort leveraging faithfulness in abstractive text summarization with elementary discourse units
url https://journals.flvc.org/FLAIRS/article/view/138888
work_keys_str_mv AT narjesdelpisheh leveragingfaithfulnessinabstractivetextsummarizationwithelementarydiscourseunits
AT ylliaschali leveragingfaithfulnessinabstractivetextsummarizationwithelementarydiscourseunits