Research
Automatic Text Summarization
Shreejeet Bhabal
Methodology/Architectural Design
Automatic Text summarization reduces the size of a source text while maintaining its information value and overall meaning. Automatic Text summarization has become a
Information overload is one of the most important concerns that has occurred as a result powerful technique for analyzing text information due to the large amount of information we are given and the growth of Internet technologies. The automatic summarization
of text is a well-known task in natural language processing (NLP). Automatic text summarization is an exciting research area, and it has a treasure of applications. This paper
of the Internet's rapid expansion. Many people will benefit from the simplification of aims to make readers understand automatic text summarization from the ground level and familiarise them with all detailed types of ATS systems. After that, all different types
are distinguished deeply and clearly in this study. The summarization task is mainly divided into extractive and abstractive. The study shows numerous techniques for extractive
pertinent information into a summary as there is a wealth of information available on the summarization, but the summaries generated by extractive summarizers are far from human-made summaries. On the other hand, an abstractive summarizer is close to human
summaries but not practically implemented with high performance. The combination of both extractive and abstractive is a hybrid text summarization. This paper includes a
Internet regarding any subject. For most people, manually summarizing large volumes of research survey on Extractive, Abstractive, and Hybrid Text Summarization. Also, this survey article tried to cover all major application areas of the ATS system and provided
a detailed survey on the same. There are so many methods to evaluate summarizing systems and generated summaries that are included in this paper. Further, it gives a brief
text can be very difficult. As a result, there is now a greater need for elaborate and potent idea about frequently used datasets, conferences, and programs that are held every year for automatic text summarization systems.
summarizers. Since the 1950s, researchers have worked to enhance methods for
summarizing information such that the summaries produced by machines and humans
coincide. This work offers a thorough, up-to-date overview of text summarizing
principles, including methodologies, procedures, standard datasets, assessment criteria,
and future research directions. The most commonly accepted approaches are extractive
and abstractive, studied in detail in this work. Evaluating the summary and increasing the
devQelopment of reusable resources and infrastructure aids in comparing and replicating
findings, adding competition to improve the outcomes. Different evaluation methods of
generated summaries are also discussed in this study. Finally, at the end of this study,
several challenges and research opportunities related to text summarization research are
mentioned that may be useful for potential researchers working in this area.
Background Information Text Summary: Sample
[1] Ahmad T. Al-Taani. “,Automatic Text Summarization Approaches” International Conference on Infocom
Various studies demonstrate the potential of NLP and machine learning for text summarization. Technologies and Unmanned Systems (ICTUS'2017)
[2] Neelima Bhatia, ArunimaJaiswal, “Automatic Text Summarization: Single and Multiple Summarizations
However, there is still room for improvement. For example, the accuracy of text summarization
”, International Journal of Computer Applications
models can be improved by using more data and by using more sophisticated machine learning
[3] Mehdi Allahyari, SeyedaminPouriyeh, Mehdi Assefi, SaeidSafaei, Elizabeth D. Trippe, Juan B. Gutierrez,
algorithms. In addition to this, there is a growing body of research on the use of machine learning
KrysKochut, “ Text Summarization Techniques: A Brief Survey”, (IJACSA) International Journal of
models for text summarization. For example, a 2021 study found that text summarization machine Advanced Computer Science and Applications
learning models can be used to reduce the reading time and improve productivity. Overall, the [4]Pankaj Gupta, Ritu Tiwari and NirmalRobert,”Sentiment Analysis and Text Summarization of Online
current state of research on text summarization using NLP and machine learning is very promising. Reviews: A Survey”InternationalConzatiference on Communication and Signal Processing,August 2013
There is a growing body of evidence that these technologies can be used to develop accurate [5]Vishalgupta,Gurpreet Singh Lehal,”A Survey of Text Summarization Extractive Techniques.”JOURNAL
summaries of huge amounts of data. These summaries can then be used to reduce reading time and Home Page Text Input Summary of Input Text
OF EMERGING TECHNOLOGIES IN WEB INTELLIGENCE, VOL. 2, NO. 3, AUGUST 2010
improve efficiency, thereby increasing the productivity. [6]Jiwei Tan, XiaojunWan,Jianguo Xiao Institute of Computer Science and Technology,Peking University
A number of published papers have investigated the use of Natural Language Processing and “Abstractive document summarization with a GraphBased attentional neural model. ”
Machine Learning for text summarization. The following is a summary of some of the key findings [7]N. D. (2016). Automatic Text Summarization Using Supervised Machine Learning Technique for Hindi
from these papers: Langauge. International Journal of Research in Engineering and Technology, 05(06), 361–367.
Automatic Text Summarization System using Natural Language Processing is a promising area of https://doi.org/10.15623/ijret.2016.0506065
[8]Ab, A., & Sunitha, C. (n.d.). An Overview on Document Summarization Techniques. 113–118. [9]Al-
research with the potential to make a significant contribution to reducing the burden of reading and
Radaideh, Q. A., & Bataineh, D. Q. (2018a). A Hybrid Approach for Arabic Text Summarization Using
analyzing large amounts of data. NLP can be used to integrate data from a variety of sources. This
Domain Knowledge and Genetic Algorithms. Cognitive Computation, 10(4), 651–669.
data can then be used to develop machine learning models to summarize input texts. Once a machine
https://doi.org/10.1007/s12559-018-9547-z
learning model has been developed, it can be used to create comprehensive summaries.
[10]Al-Radaideh, Q. A., & Bataineh, D. Q. (2018b). A Hybrid Approach for Arabic Text Summarization
File Input Summary of Input File Input Error Using Domain Knowledge and Genetic Algorithms. Cognitive Computation, 10(4), 651–669.
https://doi.org/10.1007/s12559-018-9547-z
