Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
In the digital age, the volume of textual information available to users has grown exponentially, making it
increasingly challenging to extract key insights quickly from large books and documents. This project presents an
AI-based book summary generator that leverages cutting-edge Natural Language Processing (NLP) techniques
and Transformer models to automate the summarization process. The system is designed to accept input in either
.txt or .pdf format and produce a coherent and concise summary of the content. At its core, the project utilizes the
T5 (Text-to-Text Transfer Transformer) model, a powerful pre-trained sequence-to-sequence transformer
architecture developed by Google. The model is fine-tuned for summarization tasks, allowing it to interpret and
condense complex textual data into meaningful short-form content. The program reads the input text, processes it
to remove formatting noise, and splits it into manageable chunks if it exceeds model input limits (512 tokens).
Each chunk is summarized individually, and the partial outputs are combined into a final summary. The system
handles both short and long documents effectively, offering real-time performance for small files and scalable
processing for larger texts. PDF parsing is managed using reliable Python libraries to ensure accurate text
extraction, even from multi-page documents. Additionally, the generated summary can be saved locally for future
reference. This project demonstrates the practical application of NLP in automating content understanding and
reduction, with potential use cases in academic research, publishing, journalism, and personalized reading
assistants. By minimizing the time required to grasp the essence of lengthy content, the system empowers users
to make faster, more informed decisions. Future enhancements may include GUI integration, multilingual support,
abstractive and extractive hybrid summarization, and summarization quality scoring metrics.
Keywords:
Natural Language Processing (NLP), Text Summarization, AI-Based Summarizer, Deep Learning, PDF/Text File Summarization, Sequence-to-Sequence Model, Document Summarizer, Machine Learning, Automated Book Summarization, PyTorch.
Cite Article:
"AI-Based Book Summary Generator Using NLP and Transformer Models", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 7, page no.a698-a706, July-2025, Available :http://www.ijrti.org/papers/IJRTI2507076.pdf
Downloads:
000436
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator