EXABSUM: a new text summarization approach for generating extractive and abstractive summaries
Abstract Due to the exponential growth of online information, the ability to efficiently extract the most informative content and target specific information without extensive reading is becoming increasingly valuable to readers. In this paper, we present 'EXABSUM,' a novel approach to Aut...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2023-10-01
|
Series: | Journal of Big Data |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40537-023-00836-y |
_version_ | 1797452307702480896 |
---|---|
author | Zakariae Alami Merrouni Bouchra Frikh Brahim Ouhbi |
author_facet | Zakariae Alami Merrouni Bouchra Frikh Brahim Ouhbi |
author_sort | Zakariae Alami Merrouni |
collection | DOAJ |
description | Abstract Due to the exponential growth of online information, the ability to efficiently extract the most informative content and target specific information without extensive reading is becoming increasingly valuable to readers. In this paper, we present 'EXABSUM,' a novel approach to Automatic Text Summarization (ATS), capable of generating the two primary types of summaries: extractive and abstractive. We propose two distinct approaches: (1) an extractive technique (EXABSUMExtractive), which integrates statistical and semantic scoring methods to select and extract relevant, non-repetitive sentences from a text unit, and (2) an abstractive technique (EXABSUMAbstractive), which employs a word graph approach (including compression and fusion stages) and re-ranking based on keyphrases to generate abstractive summaries using the source document as an input. In the evaluation conducted on multi-domain benchmarks, EXABSUM outperformed extractive summarization methods and demonstrated competitiveness against abstractive baselines. |
first_indexed | 2024-03-09T15:07:17Z |
format | Article |
id | doaj.art-6005c6aabda94151b11bfb6db0623fa4 |
institution | Directory Open Access Journal |
issn | 2196-1115 |
language | English |
last_indexed | 2024-03-09T15:07:17Z |
publishDate | 2023-10-01 |
publisher | SpringerOpen |
record_format | Article |
series | Journal of Big Data |
spelling | doaj.art-6005c6aabda94151b11bfb6db0623fa42023-11-26T13:35:27ZengSpringerOpenJournal of Big Data2196-11152023-10-0110113410.1186/s40537-023-00836-yEXABSUM: a new text summarization approach for generating extractive and abstractive summariesZakariae Alami Merrouni0Bouchra Frikh1Brahim Ouhbi2LIASSE Lab, National School of Applied Sciences (ENSA), Sidi Mohamed Ben Abdellah UniversityLIASSE Lab, National School of Applied Sciences (ENSA), Sidi Mohamed Ben Abdellah UniversityMathematical Modeling and Computer Laboratory (LM2I), National Higher School of Arts and Crafts (ENSAM), Moulay Ismail University (UMI)Abstract Due to the exponential growth of online information, the ability to efficiently extract the most informative content and target specific information without extensive reading is becoming increasingly valuable to readers. In this paper, we present 'EXABSUM,' a novel approach to Automatic Text Summarization (ATS), capable of generating the two primary types of summaries: extractive and abstractive. We propose two distinct approaches: (1) an extractive technique (EXABSUMExtractive), which integrates statistical and semantic scoring methods to select and extract relevant, non-repetitive sentences from a text unit, and (2) an abstractive technique (EXABSUMAbstractive), which employs a word graph approach (including compression and fusion stages) and re-ranking based on keyphrases to generate abstractive summaries using the source document as an input. In the evaluation conducted on multi-domain benchmarks, EXABSUM outperformed extractive summarization methods and demonstrated competitiveness against abstractive baselines.https://doi.org/10.1186/s40537-023-00836-yExtractive and abstractive summarizationGraph-based approachKeyphrase-based approach |
spellingShingle | Zakariae Alami Merrouni Bouchra Frikh Brahim Ouhbi EXABSUM: a new text summarization approach for generating extractive and abstractive summaries Journal of Big Data Extractive and abstractive summarization Graph-based approach Keyphrase-based approach |
title | EXABSUM: a new text summarization approach for generating extractive and abstractive summaries |
title_full | EXABSUM: a new text summarization approach for generating extractive and abstractive summaries |
title_fullStr | EXABSUM: a new text summarization approach for generating extractive and abstractive summaries |
title_full_unstemmed | EXABSUM: a new text summarization approach for generating extractive and abstractive summaries |
title_short | EXABSUM: a new text summarization approach for generating extractive and abstractive summaries |
title_sort | exabsum a new text summarization approach for generating extractive and abstractive summaries |
topic | Extractive and abstractive summarization Graph-based approach Keyphrase-based approach |
url | https://doi.org/10.1186/s40537-023-00836-y |
work_keys_str_mv | AT zakariaealamimerrouni exabsumanewtextsummarizationapproachforgeneratingextractiveandabstractivesummaries AT bouchrafrikh exabsumanewtextsummarizationapproachforgeneratingextractiveandabstractivesummaries AT brahimouhbi exabsumanewtextsummarizationapproachforgeneratingextractiveandabstractivesummaries |