Search 250 million research papers

Automatic Summarization

Huaping Zhang, Jianyun Shang · 2025

Cited by 0

Automatic Summarization

Martha Larson · now publishers, Inc. eBooks · 2012

Speech media, i.e., digital audio and video containing spoken content, has blossomed in recent years. Large collections are accruing on the Internet as well as in private and enterprise settings. This growth has motivated extensive research work on techniques and technologies that facilitate reliable indexing and retrieval. Spoken content retrieval (SCR) requires a combination of audio and speech processing technologies with methods from information retrieval (IR). SCR research initially investigated planned speech structured in document-like units, but has subsequently shifted focus to more informal spoken content produced spontaneously, outside of the studio and in conversational settings. This survey provides an overview of the field of SCR encompassing component technologies, the relationship of SCR to text IR and automatic speech recognition and user interaction issues. It is aimed at researchers with backgrounds in speech technology or information retrieval who are seeking deeper insight on how these fields are integrated to support research and development addressing the core challenges of SCR.

Cited by 14

Automatic Summarization

2008

Summarization—the art of abstracting key content from one or more information sources—has become an integral part of everyday life. People keep abreast of world affairs by listening to news bites. They base investment decisions on stock market updates. They even go to movies largely on the basis of reviews they’ve seen. With summaries, they can make effective decisions in less time. Although some summarizing tools are already available, with the increasing volume of online information, it is becoming harder to generate meaningful and timely summaries. Tools such as Microsoft’s AutoSummarize option in Office 97, IBM’s Intelligent Text Miner, Oracle’s Context, and Inxight’s Summarizer (part of

Cited by 0

Automatic Summarization

Ani Nenkova, Kathleen McKeown · Foundations and Trends® in Information Retrieval · 2011

It has now been 50 years since the publication of Luhn’s seminal paper on automatic summarization. During these years the practical need for automatic summarization has become increasingly urgent and numerous papers have been published on the topic. As a result, it has become harder to find a single reference that gives an overview of past efforts or a complete view of summarization tasks and necessary system components. This article attempts to fill this void by providing a comprehensive overview of research in summarization, including the more traditional efforts in sentence extraction as well as the most novel recent approaches for determining important content, for domain and genre specific summarization and for evaluation of summarization. We also discuss the challenges that remain open, in particular the need for language generation and deeper semantic understanding of language that would be necessary for future advances in the field.

Cited by 282

Automatic Speech Summarization

Applied To English, Chiori Hori, Sadaoki Furui et al. · 2002

This paper reports an automatic speech summarization method and experimental results using English broadcast news speech. In our proposed method, a setof words maximizing a summarization score indicating an appropriatenessof summarization is extractedftr automatically transcribed speech. This extraction is perfEG)J using a Dynamic Programming (DP) technique according to a target compression ratio. We have previously tested the perf))JdqV of our method using apanese broadcast news speech. Since our method is based on a statistical approach, it could be applied to any language. In this paper, English broadcast news speech transcribed using a speech recognizer is automatically summarized. In order to apply our method to English, the modelof estimating word concatenation probabilities based on a dependency structure in the original speech given by a Stochastic Dependency Context Free Grammar (SDCFG) is modified. A summarization methodf) multiple utterances using two-level DP technique is also proposed.

Cited by 0

Automatic Video Summarization

Itheri Yahiaoui, Bernard Merialdo, Benoit Huet · 2001

In this paper, we present a new approach for the automatic construction of video summaries. We introduce the Simulated User Principle to evaluate the quality of a video summary in a way which is automatic, yet related to user perception. We present experimental results to support our ideas.

Cited by 0

Automatic Text Summarization

Salvador Climent Roca · SHILAP Revista de lepidopterología · 2001

The coming of the WWW and of the Internet as a telecommunications network has changed the concept of what is considered information: the person who is best informed is not the one with the most information but the one with the best means for obtaining and assimilating (consuming) exactly the information acquired. This situation is proving to be a great stimulus for research into and the development of applications in the field of technology for recovering and extracting information. In this context, automated document summary systems are a new step forward towards optimising the treatment of documentation in digital formats and for tailoring it to the needs of users. This article outlines the main lines of research into the creation of automated summaries and its relationships with other areas of linguistic engineering.

Cited by 0Open access

Automatic Text Summarization

S Soumya, Geethu S. Kumar, Rasia Naseem et al. · Communications in computer and information science · 2011

Cited by 10

Automatic Video Summarization

Bernard Merialdo, Benoit Huet, Itheri Yahiaoui et al. · 2008

ABSTRACT * In this paper, we present a new approach to combine text and video in the automatic construction of summaries for audio-video sequences. This extends our previous work which was based on video only. Here, we generalize the Maximum Recollection Principle we were employing and we show how this same principle can be used to build summaries from text, based on several strategies. We present some experimental results in the evaluation of these strategies. Finally, we show how this novel principle can be used to combine text and video information for automatic summarization.

Cited by 0

Automatic document summarization

Chen, Fan · DR-NTU (Nanyang Technological University) · 2019

The information available online has been increasing exponentially and it is not going to slow down. The ability to extract information efficiently out from these huge data becomes crucial and necessary. As a result, document summarization as a part of Natural Language Processing (NLP), gains its attention by the machine learning community.
\n
\nThis project aims to explore the latest breakthrough by Google, BERT, as part of the research and how to use part of its feature and enhance our summarization system. This report will explain some of the technique behind the building of BERT and concentrates on the feature, encoding, that this project used. This report will also include the setup and the parameter and algorithm used for this project in order for continuation of this project for future reference.

Cited by 0

Automatic Text Summarization

Saraiva, João Pedro Abrantes · UBibliorum repositorio digital da ubi (University of Beira Interior) · 2021

Writing text was one of the first ever methods used by humans to represent their knowledge. Text can be of different types and have different purposes. Due to the evolution of information systems and the Internet, the amount of textual information available has increased exponentially in a worldwide scale, and many documents tend to have a percentage of unnecessary information. Due to this event, most readers have difficulty in digesting all the extensive information contained in multiple documents, produced on a daily basis. A simple solution to the excessive irrelevant information in texts is to create summaries, in which we keep the subject’s related parts and remove the unnecessary ones. In Natural Language Processing, the goal of automatic text summarization is to create systems that process text and keep only the most important data. Since its creation several approaches have been designed to create better text summaries, which can be divided in two separate groups: extractive approaches and abstractive approaches. In the first group, the summarizers decide what text elements should be in the summary. The criteria by which they are selected is diverse. After they are selected, they are combined into the summary. In the second group, the text elements are generated from scratch. Abstractive summarizers are much more complex so they still need a lot of research, in order to represent good results. During this thesis, we have investigated the state of the art approaches, implemented our own versions and tested them in conventional datasets, like the DUC dataset. Our first approach was a frequency­based approach, since it analyses the frequency in which the text’s words/sentences appear in the text. Higher frequency words/sentences automatically receive higher scores which are then filtered with a compression rate and combined in a summary. Moving on to our second approach, we have improved the original TextRank algorithm by combining it with word embedding vectors. The goal was to represent the text’s sentences as nodes from a graph and with the help of word embeddings, determine how similar are pairs of sentences and rank them by their similarity scores. The highest ranking sentences were filtered with a compression rate and picked for the summary. In the third approach, we combined feature analysis with deep learning. By analysing certain characteristics of the text sentences, one can assign scores that represent the importance of a given sentence for the summary. With these computed values, we have created a dataset for training a deep neural network that is capable of deciding if a certain sentence must be or not in the summary. An abstractive encoder­decoder summarizer was created with the purpose of generating words related to the document subject and combining them into a summary. Finally, every single summarizer was combined into a full system. Each one of our approaches was evaluated with several evaluation metrics, such as ROUGE. We used the DUC dataset for this purpose and the results were fairly similar to the ones in the scientific community. As for our encoder­decode, we got promising results.

Cited by 0Open access

Automatic Text Summarization

Sakshi Jawale, Pranit Londhe, Prajwali Kadam et al. · International Journal for Research in Applied Science and Engineering Technology · 2023

Abstract: Text Summarization is a Natural Language Processing (NLP) method that extracts and collects data from the source and summarizes it. Text summarization has become a requirement for many applications since manually summarizing vast amounts of information is difficult, especially with the expanding magnitude of data. Financial research, search engine optimization, media monitoring, question-answering bots, and document analysis all benefit from text summarization. This paper extensively addresses several summarizing strategies depending on intent, volume of data, and outcome. Our aim is to evaluate and convey an abstract viewpoint of the present scenario research work for text summarization.

Cited by 2Open access

Automatic Text Summarization

2008

Abstract—This work proposes an approach to address automatic text summarization. This approach is a trainable summarizer, which takes into account several features, including sentence position,

Cited by 0

Automatic Text Summarization

Riya Kamble, Saurabh Shah, Aalok Nerurkar et al. · 2018

Cited by 0

Automatic Summarization of

English Broadcast News, Chiori Hori, Sadaoki Furui et al. · 2002

This paper proposes an automatic speech summarization technique for English. In our proposed method, a set of words maximizing a summarization score indicating appropriateness of summarization is extracted from automatically transcribed speech and concatenated to create a summary. The extraction process is performed using a Dynamic Programming (DP) technique according to a target compression ratio. In this paper, English broadcast news speech transcribed using a speech recognizer is automatically summarized. In order to apply our method, originally proposed for Japanese, to English, the model of estimating word concatenation probabilities based on a dependency structure in the original speech given by a Stochastic Dependency Context Free Grammar (SDCFG) is modified. A summarization method for multiple utterances using twolevel DP technique is also proposed. The automatically summarized sentences are evaluated by a summarization accuracy based on the comparison with the manual summarization of correctly transcribed speech by human subjects. Experimental results show that our proposed method effectively extracts relatively important information and remove redundant and irrelevant information from English news speech.

Cited by 0

Automatic Text Summarization

Salvador Climent Roca · Digithum · 2001

The electronic journal Digithum is designed for academics, professionals and students from the various fields relating to the humanities and social sciences and is published with the following aims in mind: The distribution/publication of editorial articles or research results in the following subject areas: The knowledge society: analysis of the transformations taking place in the digital age in terms of the humanities and social sciences. By information or knowledge society, we mean the current state of evolution of society, where generalised use of information and communication technologies (ICT) in the production and exchange of information determines the evolution and transformation of social life, politics and the economy - especially, but not only, in developed countries. The transformation towards the knowledge society is having effects on the foundations of the organisation and structuring of societies in a way that involves a range of processes that are configuring a new social context or environment. These processes are linguistic, cultural, political and economic globalisation; the conversion of information into a raw material, and the re-establishing of social identity. The repercussions of information and communication technologies (ICT) on studies, teaching and the dissemination of the humanities and social sciences. ICT applications in studies, teaching or the dissemination of the humanities and social sciences. Promoting, in the academic community and amongst its readers, regular debate on the journal's subject matter, which, in principle, is to be related to the dossier. Digithum also reserves space for the distribution of certain articles which, though not strictly fitting into the aforementioned subject areas, due to their quality or relevance represent an important contribution to fields of study in the humanities and social sciences.

Cited by 12Open access

Automatic Text Summarization

Chengqing Zong, Rui Xia, Jiajun Zhang · 2021

Cited by 10

Automatic text summarization

T.Suresh Kumar · 2014

Automatic summarization is the procedure of decreasing the content of a document with a machine (computer) program so as to make a summary that holds the most critical sentences of the text file (document). Extracting summary from the document is a difficult task for human beings. Therefore to generate summary automatically has to facilitate several challenges; as the system automates it can only extract the required information from the original document. As the issue of information overload has grown - trouble has been initiated, and as the measure of data has extended, so has eagerness to customize it. It is uncommonly troublesome for individuals to physically condense broad reports of substance. Automatic Summarization systems may be classified into extractive and abstractive summary. An extractive summary method involves selecting indispensable sentences from the record and interfacing them into shorter structure. The vitality of sentences chosen is focused around factual and semantic characteristics of sentences. Extractive method work by selecting a subset of existing words, or sentences in the text file (content document) to produce the summary of input text file. The looking of important data from a huge content document is exceptionally difficult occupation for the user consequently to programmed concentrate the imperative information or summary of the content record. This summary helps the users to reduce time instead Of reading the whole text document and it provide quick knowledge from the large text file. The extractive summarization are commonly focused around techniques for sentence extraction to blanket the set of sentences that are most important for the general understanding of a given text file. In frequency based technique, obtained summary makes more meaning. But in k-means clustering due to out of order extraction, summary might not make sense.

Cited by 0

Automatic Text Summarization

Harshit Garg, Harshit Vijayvergiya, Anidhya Athaiya · 2020

The amount of data available to us both online and offline is growing extremely and due to this summarization became increasingly importantover the past few years. Automatic Summarization is the process of reducing a document to a small document called summary that containsthe significant or key points of the original document. Automatic Text Summarization is broadly classified into two categories i.e Extractive Summarization and Abstractive Summarization. Extractive Summary is a subset of the original document that represents important data contained in the document. An abstractive summary may contain some novel sentences that are not present in the whole document. In this context we are working on extractive summarization where we are including important sentences from the document in the summary with limited length. Automatic summarization is a technique by which the data is extracted and shorten from text document by the use of software .

Cited by 0

Text Summarization Using Automatic Text Summarization

K Ashwini, Shreyas Sen, K Shreyas · 2025

The rapid emergence of multimedia technologies as well as the Internet saw a rise in the volumes of text data. Such huge amounts of text may give some insights that need to be properly distilled. The distillation of all content and its meaning without changing any aspect of a long source text is called text summarisation. This paper discusses the most widely used ATS architectures together with a detailed overview of ATS. The explosion of multimedia applications and the Internet has made an exponential growth of text data. Such massive amount of textual content may contain insights to be summarized appropriately. The task of condensing a lengthy source text preserving its content and relevance is called text summarization.

Cited by 0