Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{205030,
        author = {Devesh Kumar Yadav and Balwant Kumar and Shachi Mall},
        title = {Enhancing Text Summarization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {5563-5568},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205030},
        abstract = {In the proposed project, an extensive analysis and implementation of different text summarization architectures using deep learning techniques have been provided. In this context, it is mentioned that the proposed system includes an extensive analysis and implementation of different text summarization techniques using deep learning techniques. In this context, it is mentioned that the proposed system includes an extensive analysis and implementation of different text summarization techniques using deep learning techniques, including extractive text summarization techniques and abstractive text summarization techniques using transformer architectures. In this context, it is mentioned that in the proposed system, the BERT encoder model, i.e., bert-base-uncased, is used to select the most important sentences in the text using a classification layer over contextual embeddings. Furthermore, in this context, it is mentioned that a custom sequence-to-sequence model using LSTM architecture is used in the proposed system to implement abstractive text summarization techniques using an encoder mechanism and a decoder mechanism with attention techniques to generate text summaries. Moreover, in this context, it is mentioned that state-of-the-art text summarization techniques using T5 and BART architectures, i.e., transformer architectures, are used in the proposed system to generate text summaries. As per the experimental analysis, it is concluded that the proposed system using state-of-the-art architectures outperforms other text summarization techniques in terms of fluency, coherence, and contextual understanding. Thus, it is concluded that the proposed project includes an extensive analysis and implementation of traditional deep learning architectures using state-of-the-art architectures.},
        keywords = {BERT, LSTM, Deep Learning, Text Summarization and Transformer.},
        month = {June},
        }