Citation :

Yuvraj Singh, Anuradha Misra, 2026. "Extractive and Abstractive Hybrid Summarization Model " ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 2: 31-38.

Abstract :

In an era of rapidly increasing digital content, the ability to efficiently process and comprehend large volumes of textual data has become essential. Automatic text summarization, a fundamental task within Natural Language Processing (NLP), seeks to condense lengthy documents into shorter, coherent summaries without losing essential information. This research presents the development and deployment of an extractive text summarization system that leverages NLP and machine learning techniques to provide accurate and efficient summarization. The proposed system utilizes the spaCy language model for natural language understanding, including tokenization, part-of-speech tagging, and syntactic dependency parsing. A frequency-based algorithm is applied to compute word importance, which is subsequently used to score and rank sentences. The most informative sentences are selected to generate the final summary. The summarization system is integrated into a web-based interface using the Flask framework, enabling real-time user interaction. Users can input raw text into the web application and receive an instant, concise summary of the content. The system is designed to be computationally lightweight and suitable for deployment on standard computing resources without the need for extensive training data or complex deep learning architectures. Experimental evaluation demonstrates that the summarizer effectively reduces the length of input texts by approximately 65–75%, depending on the content, while maintaining the semantic integrity of the original text. This work highlights the feasibility and effectiveness of implementing extractive summarization using accessible NLP tools and basic machine learning principles. Future enhancements may include integration with abstractive summarization models, multi-document summarization capabilities, and support for multiple languages. The system’s simplicity, performance, and ease of use make it a practical solution for various real-world applications such as news summarization, legal document analysis, and educational content condensation.

References :

[1] Lloret, E., & Palomar, M. (2012). Text summarisation in progress: a literature review. Artificial Intelligence Review, 37(1), 1-41.

[2] Benbrahim, M., & Ahmad, K. (1995). Text summarisation: The role of lexical cohesion analysis. The New Review of Document & Text Management, 1, 321-335.

[3] Lloret, E., & Palomar, M. (2013). COMPENDIUM: a text summarisation tool for generating summaries of multiple purposes, domains, and genres. Natural Language Engineering, 19(2), 147-186.

[4] Fang, W., Jiang, T., Jiang, K., Zhang, F., Ding, Y., & Sheng, J. (2020). A method of automatic text summarisation based on long short-term memory. International Journal of Computational Science and Engineering, 22(1), 39-49.

[5] Suleiman, D., & Awajan, A. (2020). Deep learning based abstractive text summarization: approaches, datasets, evaluation measures, and challenges. Mathematical problems in engineering, 2020(1), 9365340.

[6] Lal, N. M., Krishnanunni, S., Vijayakumar, V., Vaishnavi, N., Siji Rani, S., & Deepa Raj, K. (2021). A novel approach to text summarisation using topic modelling and noun phrase extraction. In Advances in Computing and Network Communications: Proceedings of CoCoNet 2020, Volume 2 (pp. 285-298). Singapore: Springer Singapore.

[7] Garcia Constantino, M. (2013). On the use of text classification methods for text summarisation (Doctoral dissertation, University of Liverpool).

[8] Vijay, S., Rai, V., Gupta, S., Vijayvargia, A., & Sharma, D. M. (2017, December). Extractive text summarisation in hindi. In 2017 International Conference on Asian Language Processing (IALP) (pp. 318-321). IEEE.

[9] Hellesoe, L. J. (2022). Automatic domain-specific text summarisation with deep learning approaches. Auckland, New Zealand: Auckland University of Technology.

[10] Joshi, M. (2019). Semantification of text through summarisation (Doctoral dissertation, Ulster University).

[11] Bhalla, S., Verma, R., & Madaan, K. (2017). Comparative Analysis of Text Summarisation Techniques. y (IJERT), 2278-0181.

[12] Siwach, M., Mann, S., Jain, S., & Rauthan, J. (2022). Extractive text summarisation techniques-a survey. Int J Res Eng Technol, 9, 589-593.

[13] Hachey, B., & Grover, C. (2004, July). A rhetorical status classifier for legal text summarisation. In Text summarization branches out (pp. 35-42).

[14] Xia, M. (2019). Text readability and summarisation for non-native reading comprehension (Doctoral dissertation).

[15] Tzouridis, E., Nasir, J. A., & Brefeld, U. (2014, August). Learning to summarise related sentences. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers (pp. 1636-1647).

Keywords :

Natural Language Processing (NLP), Text Summarization, Extractive Summarization, spaCy, Machine Learning, Flask Web Application.