Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Literature Review
Research Methodology
Document Frequency-Term Frequency Inverse Method
Method Based on Clusters
Results and Discussion
Conclusion
References

A Comparative Study of Various Text Summarization Methods

Profile image of Kunduru Sai Sambha Shiva ReddyKunduru Sai Sambha Shiva ReddyProfile image of Chinni Sai Raj DheerajChinni Sai Raj Dheeraj

2024, International Journal of Novel Research and Development

Abstract

Text summarization refers to the process of condensing long texts into short notes while keeping the most significant information, it is an application of natural language processing. This research provides an overview of text summarization methods that make use of different technologies such as natural language processing and machine learning. Considering many approaches, including extractive and abstractive summarising techniques, and discussing the benefits and drawbacks of each. Furthermore, the role that machine learning techniques such as convolutional neural networks (CNNs), transformer models like BERT and recurrent neural networks (RNNs) play in automating the summarization process is discussed. This study also highlights certain important factors, such as maintaining coherence and evaluating summary quality. Study concludes by discussing potential directions for creating text summarization techniques in future those making use of machine learning and natural language processing techniques. Factors such as Context Relevance, Keyword count, Accuracy, Framing and Decrease in the word count are manually evaluated for each technique. TF-IDF Method, Method based on Clusters, Neural Networks and UML based Text summarisation methods are some which are considered for evaluation. This paper presents the key findings and research gaps after studying the most cited research works.

Related papers

A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding
Arthur Nery

arXiv (Cornell University), 2023

We provide a literature review about Automatic Text Summarization (ATS) systems. We consider a citation-based approach. We start with some popular and well-known papers that we have in hand about each topic we want to cover and we have tracked the "backward citations" (papers that are cited by the set of papers we knew beforehand) and the "forward citations" (newer papers that cite the set of papers we knew beforehand). In order to organize the different methods, we present the diverse approaches to ATS guided by the mechanisms they use to generate a summary. Besides presenting the methods, we also present an extensive review of the datasets available for summarization tasks and the methods used to evaluate the quality of the summaries. Finally, we present an empirical exploration of these methods using the CNN Corpus dataset that provides golden summaries for extractive and abstractive methods.

View PDFchevron_right
Text Summarization using Extractive and Abstractive Techniques
International Journal of Scientific Research in Computer Science, Engineering and Information Technology IJSRCSEIT

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2022

There have been considerable advancements in Text Summarization over the last few years. There are two ways to text summarization: one is based on natural language processing (NLP), and the other is based on deep learning. In the realm of NLP, text summarization is the most intriguing and challenging task. NLP stands for Natural Language Processing, which studies and manipulates human language by computers. Because of the massive increase in information and data, it has become critical. Text summarization is creating a thorough and meaningful summary of text from various sources such as books, news stories, research papers, and tweets, among others. Large text documents that are difficult to summarize manually are the research subject. The job of condensing a piece of text into a shorter version, minimizing the size of the original text while maintaining key informative components and content meaning, is known as summarising. Because human text summarising is a time-consuming and intrinsically tiresome process, automating it is gaining popularity and hence acts as a potent stimulus for academic study.

View PDFchevron_right
A Comparative Study of Automatic Text Summarization Methodologies
IRJET Journal

IRJET, 2022

Due to the abundance of available documents and materials all over the internet and various archives, it is becoming difficult for human users to obtain crisp information about a specific topic on time. Therefore, users need to obtain a summary of all available documents instead of a pile of documents. As manual summarization is time-consuming and not cost-effective, automatic text summarization is the need of the hour. Much research has been conducted for automatic text summarization and many solutions have been proposed. However, the automatically generated summaries are still far behind than summaries generated by human users. Most of the research has focused on generating a summary from a single document whereas generating a summary from multiple documents is becoming more important nowadays. In this paper, a survey of existing solutions for automatic text summarization has been presented and the research gaps are identified too. It is hoped that the identified research gaps would help future researchers to channelize the research in the right direction.

View PDFchevron_right
Summarization of Text Based on Deep Neural Network
IJRASET Publication

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2021

To automatically summarise a piece of content, the length of the original text must be reduced while keeping the crucial informative characteristics and meaning of the content. As a result, the automation of manual text summarization, which is a time-consuming and labor-intensive technique, is gaining popularity and is therefore a great stimulant for academic research. In today's world of information overload, abstracting and summarising large texts is crucial. Various techniques to text summarization have emerged throughout time. Traditional ways create a summary directly as a result of the document summary connection's duplication and omission. Deep learning systems have been shown to be effective in producing summaries. We focus on deep learning-based text summarization algorithms that have been developed throughout time.

View PDFchevron_right
Machine Learning Approach for Text Summarization
amita arora

International Journal of Database Theory and Application, 2017

With the abundance of interminable text documents, providing summaries can help in retrieval of relevant information very quickly. The technique is to extract those sentences from the document that contain important information. This paper presents the results of our research on extractive summarization with a method based on Support Vector Machines (SVMs). The SVMs are trained using DUC-2002 dataset and the importance of sentences is judged on the basis of salient features. To evaluate the performance of our system, comparisons are conducted with two existing methods. ROUGE scores are used to compare the system generated summaries with the human generated summaries, and the experimental results show that our system's performance achieved high metrics.

View PDFchevron_right
A Study of Different Text Summarization Techniques Based on Input
Nomi Baruah

2019

Automatic text summarization is the technique of distilling the most important information from a text or a set of text. The amount of online information services, social media and other digital format documents is increasing gradually which has necessitated intensive research in the area of automatic text summarization. Text summarization is the most challenging task for information retrieval. It requires integration of techniques, implementation of hybrid schemes, including NLP, data mining and analytics, as well as optimization and linguistic theories. Various researchers from the NLP community have been addressing it from various perspective in different domains and using different paradigms. Some summarization techniques perform well in identifying and summarizing single documents but their precision degrades sharply with multi-documents. As automatic summarization is becoming an important way to find relevant information precisely in large text in short time. This paper discus...

View PDFchevron_right
Comprehensive Survey on Abstractive Text Summarization
Vedant Patil

International Journal of Engineering Research and, 2020

Over the past few years, we have seen the rise of Automation for the purpose of human convenience. Using ML learning approach, we inch ever closer towards achieving a general purpose AI. The field of Artificial Intelligence (AI) can roughly be divided into three parts namely Machine Learning (ML), Computer Vision and Natural Language Processing (NLP). NLP involves the understanding and handling of human language of which Automatic Text Summarization is an important part. Text summarization is the process of shortening a lengthy document into a short summary. It creates fluent and coherent information while maintaining the context (meaning) of the information. It is a difficult task for human beings to generate a manual summary since it requires a rigorous analysis of the entire document. In order to reduce human efforts and time, automatic summarization techniques prove to be helpful. Text summarization has broadly two techniques, namely Extractive text summarization and abstractive text summarization. Extractive technique relies on extraction of key words, whereas in abstractive text summarization technique utilizes the principles of deep learning to generate the required summary.

View PDFchevron_right
A Survey to Automatic Summarization Techniques
PARTEEK BHATIA

2016

Abstract- This paper presents a review for automatic text summarization techniques. Text Summarization is extraction of required information from the huge documents by ignoring the irrelevant details with the help of distinct approaches and provides the summary in compact way which reduces the effort and time of user. Due to the huge availability of data in all the fields the management and study of the information become difficult. Due to this the interest in the research of new automatic summarization techniques has been increased. Different approaches are used to determine summary. Plain text and multilingual text summarization play very important role in summary generation. This paper provides the review of all the existing text summarization techniques. Keywords-Summary;UNL,NLization, UNLization;IAN; EUGENE;Multilingual.

View PDFchevron_right
Automatic Text Summarization Using a Machine Learning Approach
Celso Kaestner

Brazilian Symposium on Artificial Intelligence, 2002

In this paper we address the automatic summarization task. Recent research works on extractive-summary generation employ some heuristics, but few works indicate how to select the relevant features. We will present a summarization procedure based on the application of trainable Machine Learning algorithms which employs a set of features extracted directly from the original text. These features are of two kinds: statistical - based on the frequency of some elements in the text; and linguistic - extracted from a simplified argumentative structure of the text. We also present some computational results obtained with the application of our summarizer to some well known text databases, and we compare these results to some baseline summarization procedures.

View PDFchevron_right
Comparative Study of Text Summarization Methods
Nikita Munot

International Journal of Computer Applications, 2014

Text summarization is one of application of natural language processing and is becoming more popular for information condensation. Text summarization is a process of reducing the size of original document and producing a summary by retaining important information of original document. This paper gives comparative study of various text summarization methods based on different types of application. The paper discusses in detail two main categories of text summarization methods these are extractive and abstractive summarization methods. The paper also presents taxonomy of summarization systems and statistical and linguistic approaches for summarization.

View PDFchevron_right

References (26)

  1. D. Suleiman and A. Awajan, "Deep Learning Based Abstractive Text Summarization: Approaches, Datasets, Evaluation Measures, and Challenges," Math. Probl. Eng., vol. 2020, 2020, doi: 10.1155/2020/9365340.
  2. S. H. B. Sri and S. R. Dutta, "A survey on automatic text summarization techniques," J. Phys. Conf. Ser., vol. 2040, no. 1, pp. 268-271, 2021, doi: 10.1088/1742-6596/2040/1/012044.
  3. Gambhir, Mahak, and Vishal Gupta. "Improved hybrid text summarization system using deep contextualized embeddings and statistical features." Multimedia Tools and Applications (2024): 1-30.
  4. M. R. Prathima and H. R. Divakar, "Automatic Extractive Text Summarization Using K-Means Clustering," Int. J. Comput. Sci. Eng., vol. 6, no. 6, pp. 782-787, 2018, doi: 10.26438/ijcse/v6i6.782787.
  5. A. Joshi, E. Fidalgo, and E. Alegre, "Deep Learning based Text Summarization: Approaches, Databases and Evaluation Measures," Int. Conf. Appl. Intell. Syst., no. Dl, pp. 1-4, 2018.
  6. A. Rajasekaran and D. R. Varalakshmi, "Review on automatic text summarization," Int. J. Eng. Technol., vol. 7, no. 3.3, p. 456, 2018, doi: 10.14419/ijet.v7i2.33.14210.
  7. Neri-Mendoza, Verónica, et al. "Generic and Update Multi-Document Text Summarization based on Genetic Algorithm." Computación y Sistemas 27.1 (2023): 269-279.
  8. Yadav, Arun Kumar, et al. "Extractive text summarization using deep learning approach." International Journal of Information Technology 14.5 (2022): 2407-2415.
  9. G. Vijay Kumar, A. Yadav, B. Vishnupriya, M. Naga Lahari, J. Smriti, and D. Samved Reddy, "Text Summarizing Using NLP," Adv. Parallel Comput., vol. 39, pp. 60-67, 2021, doi: 10.3233/APC210179.
  10. Zhang, Mengli, et al. "A comprehensive survey of abstractive text summarization based on deep learning." Computational intelligence and neuroscience 2022.1 (2022): 7132226.
  11. Gambhir, Mahak, and Vishal Gupta. "Deep learning-based extractive text summarization with word-level attention mechanism." Multimedia Tools and Applications 81.15 (2022): 20829-20852.
  12. Du, Yan, and Hua Huo. "News text summarization based on multi-feature and fuzzy logic." IEEE Access 8 (2020): 140261- 140272.
  13. Al Qassem, Lamees, et al. "Automatic Arabic text summarization based on fuzzy logic." Proceedings of the 3rd international conference on natural language and speech processing. 2019.
  14. Goularte, Fábio Bif, et al. "A text summarization method based on fuzzy rules and applicable to automated assessment." Expert Systems with Applications 115 (2019): 264-275.
  15. Sharma, Shikha, and Madan Lal Saini. "Analyzing the Need for Video Summarization for Online Classes Conducted During IJNRD2409223 International Journal Of Novel Research And Development (www.ijnrd.org) c157 c157
  16. Covid-19 Lockdown." Data, Engineering and Applications: Select Proceedings of IDEA 2021. Singapore: Springer Nature Singapore, 2022. 333-342.
  17. Premakumara, Nilantha, et al. "Optimized Text Summarization method based on fuzzy logic." 2022 2nd International Conference on Image Processing and Robotics (ICIPRob). IEEE, 2022.
  18. S. Kulshrestha and M. L. Saini, "Study for the Prediction of E-Commerce Business Market Growth using Machine Learning Algorithm," 2020 5th IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE), Jaipur, India, 2020, pp. 1-6, doi: 10.1109/ICRAIE51050.2020.9358275.
  19. Kavita Lal, Madan Lal Saini; A study on deep fake identification techniques using deep learning. AIP Conf. Proc. 15 June 2023; 2782 (1): 020155. https://doi.org/10.1063/5.0154828
  20. Y. Singh, M. Saini and Savita, "Impact and Performance Analysis of Various Activation Functions for Classification Problems," 2023 IEEE International Conference on Contemporary Computing and Communications (InC4), Bangalore, India, 2023, pp. 1-7, doi: 10.1109/InC457730.2023.10263129.
  21. M. Sohail, M. Lal Saini, V. P. Singh, S. Dhir and V. Patel, "A Comparative Study of Machine Learning and Deep Learning Algorithm for Handwritten Digit Recognition," 2023 6th International Conference on Contemporary Computing and Informatics (IC3I), Gautam Buddha Nagar, India, 2023, pp. 1283-1288, doi: 10.1109/IC3I59117.2023.10397956
  22. M. Lal Saini, B. Tripathi and M. S. Mirza, "Evaluating the Performance of Deep Learning Models in Handwritten Digit Recognition," 2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan, 2023, pp. 116-121, doi: 10.1109/ICTACS59847.2023.10390027.
  23. S. Chalechema, M. L. Saini, I. Perla and A. V. Shivanand, "Customer Segmentation Using K Means Algorithm and RFM Model," 2023 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), Greater Noida, India, 2023, pp. 393-398, doi: 10.1109/ICCCIS60361.2023.10425556.
  24. S. Mittal, R. Agarwal, M. L. Saini and A. Kumar, "A Logistic Regression Approach for Detecting Phishing Websites," 2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), Faridabad, India, 2023, pp. 76-81, doi: 10.1109/ICAICCIT60255.2023.10466221.
  25. V. Prabhas, M. Lal Saini, C. Mohith, R. Kumar and B. Tripathi, "Segmentation of E-Commerce Data Using K-Means Clustering Algorithm," 2023 Global Conference on Information Technologies and Communications (GCITC), Bangalore, India, 2023, pp. 1-6, doi: 10.1109/GCITC60406.2023.10426132.
  26. M. L. Saini, A. Patnaik, Mahadev, D. C. Sati and R. Kumar, "Deepfake Detection System Using Deep Neural Networks," 2024 2nd International Conference on Computer, Communication and Control (IC4), Indore, India, 2024, pp. 1-5, doi: 10.1109/IC457434.2024.10486659.

Related papers

Machine Learning Approach for Automatic Text Summarization Using Neural Networks
Meetkumar Patel, Adwaita Chokshi, Satyadev Vyas, Khushbu Maurya

Machine learning and deep learning, as we know, have started ruling over almost every field in the computing industry and so, has revolutionized the process of text summarization too. Automatic text summarization is an advancing realm of the natural language processing research in which concise textual summaries are generated from lengthy input documents. Extensive research has been carried out on how automatic summarization can be prosecuted through various extractive and abstractive techniques. In this paper, we address all the approaches to text summarization and present the modus operandi of an Architecture called Encoder-Decoder, under the machine learning approach. Moreover, we propose several novel implementation models for this architecture, in Keras and TensorFlow that consists of various machine learning and deep learning neural network libraries.

View PDFchevron_right
Recent Approaches for Text Summarization Using Machine Learning & LSTM0
SN RAJAN

Journal of Big Data, 2021

Nowadays, data is very rapidly increasing in every domain such as social media, news, education, banking, etc. Most of the data and information is in the form of text. Most of the text contains little invaluable information and knowledge with lots of unwanted contents. To fetch this valuable information out of the huge text document, we need summarizer which is capable to extract data automatically and at the same time capable to summarize the document, particularly textual text in novel document, without losing its any vital information. The summarization could be in the form of extractive and abstractive summarization. The extractive summarization includes picking sentences of high rank from the text constructed by using sentence and word features and then putting them together to produced summary. An abstractive summarization is based on understanding the key ideas in the given text and then expressing those ideas in pure natural language. The abstractive summarization is the latest problem area for NLP (natural language processing), ML (Machine Learning) and NN (Neural Network) In this paper, the foremost techniques for automatic text summarization processes are defined. The different existing methods have been reviewed. Their effectiveness and limitations are described. Further the novel approach based on Neural Network and LSTM has been discussed. In Machine Learning approach the architecture of the underlying concept is called Encoder-Decoder.

View PDFchevron_right
Text Summarization Approaches Using Machine Learning & LSTM
Neeraj Sirohi

2021

Due to the massive amount of online textual data generated in a diversity of social media, web, and other information-centric applications. To select the vital data from the large text, need to study the full article and generate summary also not loose critical information of text document this process is called summarization. Text summarization is done either by human which need expertise in that area, also very tedious and time consuming. second type of summarization is done through system which is known as automatic text summarization which generate summary automatically. There are mainly two categories of Automatic text summarizations that is abstractive and extractive text summarization. Extractive summary is produced by picking important and high rank sentences and word from the text document on the other hand the sentences and word are present in the summary generated through Abstractive method may not present in original text. This article mainly focuses on different ATS (Au...

View PDFchevron_right
Automated Text Summarization Using NLP Techniques: A Comprehensive Approach with Seq2Seq Encoder-Decoder Model Authors: Surabhi Saurabh Authors: Chandra 1 ; Pradnya
iJournals Academic Publications IJSHRE | IJSRC

In natural language processing (NLP), text summarization is a challenging operation that involves reducing the length of a document while retaining its key points and essential details. In this project, we propose a solution to this problem by leveraging NLP techniques to automatically generate concise summaries from text data. Our approach involves utilizing various NLP segmentation such as part-of-speech tagging, tokenization, and sentence parsing, to analyze and understand the content of the input text as well as its structure. We then apply machine learning algorithms, like RNNs and transformer models, to learn the important features and patterns of the text data. Based on these learned features, we develop a summarization model that can identify and extract relevant information from the original text. To calculate and analyze the effectiveness of our approach, we will use standard evaluation metrics, such as ROUGE (Recall-Oriented Understudy for Gisting Evaluation), to assess the quality of the generated summaries in terms of their similarity to the reference summaries. We will also conduct experiments on different types of text data, such as social media posts, news articles, and research papers, to assess the robustness and generalizability of our summarization model. The proposed project has several potential applications, including news article summarization, document summarization for information retrieval, and social media summarization for sentiment analysis. The outcome of this project is expected to contribute to the field of NLP and machine learning by providing an effective solution for text summarization, which can help users quickly and efficiently extract key information from large amounts of text data.

View PDFchevron_right
Comparative Study of Abstractive Text Summarization Techniques
IRJET Journal

IRJET, 2022

The volume of textual data has expanded exponentially in recent years, making it a nuisance to store valuable information. Mining this enormous dataset containing dissimilar structured or unstructured data to identify hidden patterns for actionable and data driven insights can be troublesome. This information must be summarized to obtain meaningful knowledge in an acceptable time. This paper examines techniques for abstractive text summarization and validates these techniques on CNN/Daily Mail dataset using ROUGE scores. In addition to the use cases, their features and limitations in the real world are presented. The difficulties that arise during the summarization process and the solutions put forward in each approach are scrutinized, investigated, and explored. After evaluating the various approaches, it was found that the most common strategies for abstractive text summarization are recurrent neural networks with an attention mechanism and the transformer architecture. On experimenting, the results displayed that text summarization with Pegasus large model achieved the highest values for ROUGE-1 and ROUGE-L (44.17, 41.11 respectively). A detailed study was done to see how the best results were attained by the models applying a Transformer.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved