Automatic multi document summarization approaches (original) (raw)

A Systematic Survey on Multi-document Text Summarization

International Journal of Advanced Trends in Computer Science and Engineering, 2021

Automatic text summarization is a technique of generating short and accurate summary of a longer text document. Text summarization can be classified based on the number of input documents (single document and multi-document summarization) and based on the characteristics of the summary generated (extractive and abstractive summarization). Multi-document summarization is an automatic process of creating relevant, informative and concise summary from a cluster of related documents. This paper does a detailed survey on the existing literature on the various approaches for text summarization. Few of the most popular approaches such as graph based, cluster based and deep learning-based summarization techniques are discussed here along with the evaluation metrics, which can provide an insight to the future researchers.

Multi Document Summarization: Approaches and Future Scope

2015

With rapid growth of world wide web, the amount of quickly growing information has gone beyond our imagination. Many techniques are presented to help users to find the desired information from large data set quickly and accurately. Multi document summarization is effective one. The techniques that are used in summarization are feature based, graph based, cluster based, knowledge based, component based and CST based. The outline of all the methods is discussed in detail. Then all methods are compared and future work is discussed

An Abstract Study on Non-Identical Multi-Document Summarization Approaches

2018

In the current situation the rate of development of data is growing exponentially in the World Wide Web. Thus, extricating legitimate and valuable data from enormous information has turned into a testing issue. As of late text summarization is perceived as one of the answer for remove applicable data from huge documents. Based on number of documents considered for summarization, the summarization assignment is ordered as single document or multi-document summarization. As opposed to single document, multi-document summarization is all the more trying for the analysts to discover exact synopsis from multiple documents. In this paper we have begun with presentation of multidocument summarization and after that have additionally examined examination and investigation of different methodologies which goes under the multidocument summarization. The paper additionally contains insights about the advantages and issues in the current techniques. This would particularly be useful for scientists working in this field of text information mining. By utilizing this information, scientists can fabricate new or blended based methodologies for multi-document summarization.

A Survey on Various Techniques for Multi-Document Summarization

International Journal of Scientific Research in Science and Technology, 2019

Natural language processing gives Text Summarization which is the most well-known application for data pressure. Content rundown is a procedure of creating a synopsis by decreasing the span of unique report and relating critical data of unique record. There is emerging a need to give top notch synopsis in less time on the grounds that in present time, the development of information increments massively on World Wide Web or on client's desktops so Multi-Document outline is the best apparatus for making rundown in less time. This paper introduces a study of existing techniques with the curiosities highlighting the need of astute Multi-Document summarizer.

Review of Multi-document Text Summarization Methods

2014

In today's busy schedule, everybody expects to get the information in short but meaningful manner. Huge long documents consume more time to read. For this, we need summarization of document. Work has been done on Single-document but need of multiple document summarization is encouraging. Existing methods like graph-based approach, fuzzy-genetic based approach, genetic approach and statistical approach for multiple document summaries are improving. The statistical approach based on algebraic method is still the topic of research. Effort has to be done to improve this approach by considering the limitations of Latent Semantic Analysis (LSA). Firstly, it reads only input text and does not consider world knowledge. Secondly, it does not consider word order. The different clauses may convey same meaning in different parts of document. Lastly, all the approaches give their output in text form. The approach is to bring the output in tabular form, so that LSA method can be improved.

A Survey of Multi-Document Summarization.

International Journal of Engineering Sciences & Research Technology, 2013

This paper describes a survey of Multiaims at extraction of information from a set of documents written about same topic and helps to familiarize themselves with information content in large cluster of documents. There are several strategies for selecting interesting and informative sentences from set documents. Generic and Topi Summarization are the two main strategies. This paper goes through different approaches in each strategy.

Study on Multi Document Summarization by Machine Learning Technique for Clustered Documents

International Journal of Engineering Development and Research, 2017

This paper discusses the development of multi document summarization by using different approach like abstractive-extractive summarization approach. Multi document summarization is a technology that use to summarize multiple documents and make its summary. A particular challenge for multi-document summarization is that there is an information stored in different documents. In this paper we discuss different approaches used like LSA, LDA, LDA-SVD, Semantic Graph approach etc.

Modern Multi-Document Text Summarization Techniques

International Journal of Recent Technology and Engineering

Text Summarization is the technique in which the source document is simplified, valuable information is distilled and an abridged version is produced. Over the last decade, the focus has shifted from single document to multi-document summarization and despite significant progress in the domain, challenges such as sentence ordering and fluency remain. In this paper, a thorough comparison of the several multi-document text summarization techniques such as Machine Learning based, Graph based, Game-Theory based and more has been presented. This paper in its entirety condenses and interprets the numerous approaches, merits and limitations of these techniques. The Benchmark datasets of this domain and their features have also been examined. This survey aims to distinguish the various summarization algorithms based on properties that prove to be valuable in the generation of highly consistent, rational, summaries with reduced redundancy and information richness. The conclusions presented b...

A Survey on Multi-Document Summarizer

Natural language processing provides Text Summarization which is the most popular application for information compression. Text summarization is a process of producing a summary by reducing the size of original document and pertaining important information of original document. There is arising a need to provide high quality summary in less time because in present time, the growth of data increases tremendously on World Wide Web or on user's desktops so Multi-Document summarization is the best tool for making summary in less time. This paper presents a survey of existing techniques with the novelties highlighting the need of intelligent Multi-Document summarizer.

IJERT-Literature Survey on Topic Focused Multi-Document Summarization

International Journal of Engineering Research and Technology (IJERT), 2015

https://www.ijert.org/literature-survey-on-topic-focused-multi-document-summarization https://www.ijert.org/research/literature-survey-on-topic-focused-multi-document-summarization-IJERTV4IS080599.pdf Multi-document summarization is the way of generating summaries that are highly related to human generated summaries from multiple documents that are retaining the most important characteristics of the original document. It's a process of summarizing a text by computer where a text is given to the computer as input and the output is a shorter and less redundant. There are two approaches in multi document summarization: abstractive based summarization and extractive based summarization. In this paper, we compare various techniques done for multi-document summarization. So that in future one can gets significant instruction for further analysis.