Generative Artificial Intelligence for Automated Document Summarization and Knowledge Extraction

Émilie Dubois

Generative Artificial Intelligence for Automated Document Summarization and Knowledge Extraction

Author(s)	Émilie Dubois
Country	France
Abstract	The rapid expansion of digital information has created increasing demand for computational systems capable of condensing lengthy documents and identifying useful knowledge from large text collections. Conventional extractive summarization methods primarily select important passages from source documents, whereas generative approaches attempt to construct new textual representations of salient information. At the same time, knowledge-extraction methods identify entities, attributes, and relationships that can support structured information retrieval and downstream analytical tasks. Integrating these capabilities offers a methodological basis for more comprehensive automated document understanding. This hypothetical methodological study examines a generative artificial intelligence framework for automated document summarization and knowledge extraction. The proposed architecture combines document encoding, attention-guided sequence generation, semantic representation, relation extraction, and post-generation consistency assessment. A conceptual dataset of 600 documents is divided into hypothetical training, validation, and testing partitions. Three model configurations are considered: an extractive baseline, an attention-based generative summarizer, and an integrated generative summarization and knowledge-extraction architecture. The illustrative analysis compares the configurations using ROUGE-1, ROUGE-2, ROUGE-L, and a hypothetical factual-consistency measure. A separate knowledge-extraction analysis evaluates entity-property, binary-relation, and event-context extraction using precision, recall, and F1 score. Under the assigned values, the integrated architecture records higher summarization overlap while maintaining stronger hypothetical factual consistency than the standalone generative configuration. Knowledge-extraction performance varies across relation categories, with structured entity-property relations producing the highest illustrative F1 score. The study concludes that generative document processing may provide a useful methodological framework for combining natural-language summarization with structured knowledge extraction. However, generated summaries can omit, distort, or introduce information unless their outputs are evaluated against the source documents. The study therefore emphasizes reproducible assessment, factual verification, transparent model comparison, and separation between linguistic fluency and knowledge accuracy.
Keywords	Generative Artificial Intelligence, Automated Summarization, Knowledge Extraction, Natural Language Processing, Abstractive Summarization, Information Extraction, Sequence-to-Sequence Learning, Attention Mechanism, Relation Extraction, Document Intelligence.
Field	Engineering
Published In	Volume 1, Issue 2, May-June 2025
Published On	2025-06-26

View / Download PDF File

E-ISSN: 3067-5073

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJMLAIDSE DOI prefix is
10.00000/IJMLAIDSE

Downloads

Research Paper Format Copyright Permission and Undertaking Form

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJMLAIDSE Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	+1-872-302-3851	editor@uscse.com

International Journal of Machine Learning, AI & Data Science Evolution

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Monthly Scholarly International Journal

Generative Artificial Intelligence for Automated Document Summarization and Knowledge Extraction

Share this