article · Journal Of Big Data
The rapid growth of online information creates an urgent requirement to identify vital content without reading lengthy documents. EXABSUM offers a dual-track approach to automatic text summarisation capable of producing both extractive and abstractive outputs. The extractive component combines statistical metrics and semantic scoring to pinpoint and retrieve relevant, non-redundant sentences from a source text. Meanwhile, the abstractive component applies a word graph structure through sentence compression and fusion stages, followed by keyphrase-based re-ranking to formulate new, concise summaries directly from the source material. Tested across multi-domain benchmark datasets, the system surpasses established extractive summarisation methods and achieves competitive results when evaluated against alternative abstractive baselines.
Readers face an overwhelming volume of online text, making rapid access to essential points critical. Automated summarisation allows individuals and organisations to digest large amounts of written material quickly. Providing both sentence extraction and generated abstracts within one framework helps improve how key insights are surfaced across diverse document types.
The approach represents applied algorithmic research tested on benchmark datasets. It could enable software developers to build or enhance automated document analysis tools, knowledge management platforms, and content filtering services across multiple subject domains. However, the abstract does not indicate production deployment, software availability, or a defined commercialisation pathway, suggesting it currently sits at an experimental validation stage.
AI-generated from the published abstract. Always read the original work before citing.
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 (EXABSUM Extractive ), which integrates statistical and semantic scoring methods to select and extract relevant, non-repetitive sentences from a text unit, and (2) an abstractive technique (EXABSUM Abstractive ), 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.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1186/s40537-023-00836-y
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
