Search

Whenever there is too much information out there, it is desirable to summarize. If humans are trying to create the summary, it will take lot of time. Now to make the problem of summarizing information easier and more effortless one can automate the summarization process which can reduce the time taken in creating summary. This is called as automatic summarization. The two ways of summarization are extractive summarization and abstractive summarization. Extractive summarization and its applications have been the subject of extensive research and have received state of art solution. But abstractive summarization still is a progressive field as it is difficult to create abstractive summary as humans do. Also, it is still a question i.e., how to evaluate the quality of a summary? Therefore, this paper is a comprehensive survey on the dataset used with its details and statistics, analysis of various abstractive summarization techniques and important parameters for evaluating the quality of summary. Deep leaning based models have given new direction in this field. The author also focuses on problems and challenges faced in the generation of summary which are opening the future research scope in this domain. [ABSTRACT FROM AUTHOR]

Automatic text summarization is the task of creating concise and fluent summaries without human intervention while preserving the meaning of the original text document. To increase the readability of the languages, a summary should be generated. In this paper, a novel Nesterov-accelerated Adaptive Moment Estimation Optimization based on Long Short-Term Memory [NADAM-LSTM] has been proposed to summarize the text. The proposed NADAM-LSTM model involves three stages namely pre-processing, summary generation, and parameter tuning. Initially, the Giga word Corpus dataset is pre-processed using Tokenization, Word Removal, Stemming, Lemmatization, and Normalization for removing irrelevant data. In the summary generation phase, the text is converted to the word-to-vector method. Further, the text is fed to LSTM to summarize the text. The parameter of the LSTM is then tuned using NADAM Optimization. The performance analysis of the proposed NADAM-LSTM is calculated based on parameters like accuracy, specificity, Recall, Precision, and F1 score. The suggested NADAM-LSTM achieves an accuracy range of 99.5%. The result illustrates that the proposed NADAM-LSTM enhances the overall accuracy better than 12%, 2.5%, and 1.5% in BERT, CNN-LSTM, and RNN respectively. [ABSTRACT FROM AUTHOR]

The purpose of government news summarization is to extract the most important information from official government news reports. It is important for readers to be able to understand government news quickly in the age of information overload. Compared with other types of news, government news reports have more detailed content and possess a more normative format, resulting in greater length. To resolve the contradiction between the length of these reports and the trend of fragmented reading, this research proposes an automatic text summarization model based on multiple features. First, the features are extracted using the TF–IDF algorithm and word vector embedding method based on the bidirectional encoder representation from the transformers model. Second, we score the sentences based on the position, keywords, and similarity features. Finally, the top-ranked sentence is selected to form the summarization. To verify the effectiveness and superiority of the proposed method, Edmundson and ROUGE were adopted. First, based on the Edmundson evaluation criteria, the summarization results of various methods were scored. The score differences between ATS summarization based on the proposed method and manual summarization were minimal across consistency, grammaticality, time sequence, conciseness, and readability, with values of 0.14, 0.18, 0.12, 0.10, and 0.16, respectively. This suggests that our summarization exhibits the highest similarity to manual summarization. Second, we evaluated the summarization results using the ROUGE evaluation criteria. The results indicate that the proposed method achieved significantly higher scores compared to other models. Specifically, for character-level ROUGE-1, the P, R, and F scores reached 0.84, 0.93, and 0.88, respectively. At the word-level ROUGE-1, the P, R, and F scores were 0.81, 0.89, and 0.85, respectively, which demonstrates a noticeable improvement over other models. Furthermore, compared to manual methods, the proposed method has advantages in assisting the reader to obtain important information rapidly. [ABSTRACT FROM AUTHOR]

The rapid development of technology has resulted in a surge in the volume of digital data available. This situation creates a problem for users who need assistance in locating specific information within this massive collection of data, resulting in a time-consuming process. Automatic Text Summarization systems have been developed as a more effective solution than traditional summarization techniques to address this problem and improve user access to relevant information. It is well known that researchers in the health sciences find it difficult to keep up with the latest literature due to their busy schedules. This study aims to produce comprehensive abstracts of Turkish-language scientific papers in the field of health sciences. Although abstracts of scientific papers are already available, more thorough summaries are still needed. To the best of our knowledge, no previous attempt has been made to automatically summarize Turkish language health science papers. For this purpose, a dataset of 105 Turkish papers was collected from DergiPark. Term Frequency, Term Frequency-Inverse Document Frequency, Latent Semantic Analysis, TextRank, and Latent Dirichlet Allocation algorithms were chosen as extractive text summarization methods due to their frequent use in this field. The performance of the text summarization models was evaluated using recall, precision, and F-score metrics, and the algorithms gave satisfactory results for Turkish. [ABSTRACT FROM AUTHOR]

Nowadays, individuals can be overwhelmed by a huge number of documents being present in daily life. Capturing the necessary details is often a challenge. Therefore, it is rather important to summarize documents to obtain the main information quickly. There currently exist automatic approaches to this task, but their quality is often not properly assessed. State-of-the-art metrics rely on human-generated summaries as a reference for the evaluation. If no reference is given, the assessment will be challenging. Therefore, in the absence of human-generated reference summaries, we investigated an alternative approach to how machine-generated summaries can be evaluated. For this, we focus on the original text or document to retrieve a metric that allows a direct evaluation of automatically generated summaries. This approach is particularly helpful in cases where it is difficult or costly to find reference summaries. In this paper, we present a novel metric called Summary Score without Reference—SUSWIR—which is based on four factors already known in the text summarization community: Semantic Similarity, Redundancy, Relevance, and Bias Avoidance Analysis, overcoming drawbacks of common metrics. Therefore, we aim to close a gap in the current evaluation environment for machine-generated text summaries. The novel metric is introduced theoretically and tested on five datasets from their respective domains. The conducted experiments yielded noteworthy outcomes, employing the utilization of SUSWIR. [ABSTRACT FROM AUTHOR]

Considering the ever-growing volume of electronic documents made available in our daily lives, the need for an efficient tool to capture their gist increases as well. Automatic text summarization, which is a process of shortening long text and extracting valuable information, has been of great interest for decades. Due to the difficulties of semantic understanding and the requirement of large training data, the development of this research field is still challenging and worth investigating. In this paper, we propose an automated text summarization approach with the adaptation of static and contextual representations based on an extractive approach to address the research gaps. To better obtain the semantic expression of the given text, we explore the combination of static embeddings from GloVe (Global Vectors) and the contextual embeddings from BERT (Bidirectional Encoder Representations from Transformer) and GPT (Generative Pre-trained Transformer) based models. In order to reduce human annotation costs, we employ policy gradient reinforcement learning to perform unsupervised training. We conduct empirical studies on the public dataset, Gigaword. The experimental results show that our approach achieves promising performance and is competitive with various state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

The increasing amount of legal information available online is overwhelming for both citizens and legal professionals, making it difficult and time-consuming to find relevant information and keep up with the latest legal developments. Automatic text summarization techniques can be highly beneficial as they save time, reduce costs, and lessen the cognitive load of legal professionals. However, applying these techniques to legal documents poses several challenges due to the complexity of legal documents and the lack of needed resources, especially in linguistically under-resourced languages, such as the Greek language. In this paper, we address automatic summarization of Greek legal documents. A major challenge in this area is the lack of suitable datasets in the Greek language. In response, we developed a new metadata-rich dataset consisting of selected judgments from the Supreme Civil and Criminal Court of Greece, alongside their reference summaries and category tags, tailored for the purpose of automated legal document summarization. We also adopted several state-of-the-art methods for abstractive and extractive summarization and conducted a comprehensive evaluation of the methods using both human and automatic metrics. Our results: (i) revealed that, while extractive methods exhibit average performance, abstractive methods generate moderately fluent and coherent text, but they tend to receive low scores in relevance and consistency metrics; (ii) indicated the need for metrics that capture better a legal document summary's coherence, relevance, and consistency; (iii) demonstrated that fine-tuning BERT models on a specific upstream task can significantly improve the model's performance. [ABSTRACT FROM AUTHOR]

Due to the obvious significant expansion in the number of online Arabic textual information, Arabic Text Summarization has become a focus of intense research. Manual text summarization necessitates a large investment of time, effort, and money. Hence, Automatic Arabic Text Summarization (AATS) is currently necessary to create accurate and relevant summaries from the huge amount of accessible content. The developed techniques and methodologies for AATS are still in their immaturity because of the intrinsic complexity of the structure and morphology of the Arabic language. AATS methods could be categorized as extractive, abstractive, hybrid extractive to abstractive. The extractive method selects and combines the most important sentences from the input document(s) to produce the summary. While the abstractive method needs deep understanding of the input document(s) for creating the summary with sentences that differ from the original ones. The extractive to abstractive method is a hybrid strategy for creating an informative and cohesive summary using the extractive summary as a first step. This paper provides a detailed explanation of the fundamental issues related to Arabic text summarization. It describes and analyzes the various methods and systems currently in use, traces their history and monitors their performance. The challenges and trends are explored. [ABSTRACT FROM AUTHOR]

An abstract is the most crucial element that may convince readers to read the complete text of a scientific publication. However, studies show that in terms of organization, readability, and style, abstracts are also among the most troublesome parts of the pertinent manuscript. The ultimate goal of this article is to produce better understandable abstracts with automatic methods that will contribute to scientific communication in Turkish. We propose a summarization system based on extractive techniques combining general features that have been shown to be beneficial for Turkish. To construct the data set for this aim, a sample of 421 peer-reviewed Turkish articles in the field of librarianship and information science was developed. First, the structure of the full-texts, and their readability in comparison with author abstracts, were examined for text quality evaluation. A content-based evaluation of the system outputs was then carried out. System outputs, in cases of using and ignoring structural features of full-texts, were compared. Structured outputs outperformed classical outputs in terms of content and text quality. Each output group has better readability levels than their original abstracts. Additionally, it was discovered that higher-quality outputs are correlated with more structured full-texts, highlighting the importance of structural writing. Finally, it was determined that our system can facilitate the scholarly communication process as an auxiliary tool for authors and editors. Findings also indicate the significance of structural writing for better scholarly communication. [ABSTRACT FROM AUTHOR]

In recent years, a large amount of data has been accumulated, such as those recorded in geological journals and report literature, which contain a wealth of information, but these data have not been fully exploited or mined. Automatic information extraction offers an effective way to achieve new discoveries and pursue further analysis, which is of great significance for users, researchers or decision makers to aid and support analysis. In this paper, we utilize the bidirectional encoder representations from transformers (BERT) model, which is fine-tuned and then applied to automatically generate the title of a given input summarization based on the collection of published literature samples. The framework contains an encoder module, decoder module and training module. The core stages of summary generation involve the combination of encoder and decoder modules, and the multi-stage function is then used to connect modules, thus endowing the text summarization model with a multi-task learning architecture. Compared to other baseline models, our proposed model obtains the best results on the constructed dataset. Therefore, based on the proposed model, an automatic geological briefing generation platform is developed and used as an online platform to support the excavation of key areas and a visual presentation analysis of the literature. [ABSTRACT FROM AUTHOR]

Extractive text summarization consists of selecting the most important sentences from the original text. By summarizing the contents of the article, readers might be able to understand the article more easily and faster than reading the entire article. The process of summarizing involves gathering as much as possible of the information and presenting only the most important details as succinctly as possible. To solve that problem, a genetic algorithm will be adopted to extract sentences as a summary. The summarization process is considered as an optimization problem where the optimal summary is selected from a series of sentences from the original document. Genetic algorithm used to optimize sentence selection to obtain a summary that represents the main idea of the source document where the compression rate determines the number of sentences selected as summary. To represents the text and capture the interconnects between sentences, a graph will be constructed and given a weight with PageRank score. 60 news articles in Bahasa Indonesia from IndoSum are used as a dataset. To evaluate how good the results are, ROUGE-1 and cosine similarity are calculated to compare the summary generated by the system and reference summary. This study also set up 5 comparisons to other methods such as SumBasic, LexRank, LSA, TextRank, and KLSum. Evaluation results yield better summary results compare to other methods with the average ROUGE-1 score 0.641 on recall and cosine similarity 0.625 for compression rate of 30%. [ABSTRACT FROM AUTHOR]

Text summarization resolves the issue of capturing essential information from a large volume of text data. Existing methods either depend on the end-to-end models or hand-crafted preprocessing steps. In this study, we propose an entity-centric summarization method which extracts named entities and produces a small graph with a dependency parser. To extract entities, we employ well-known pre-trained language models. After generating the graph, we perform the summarization by ranking entities using the harmonic centrality algorithm. Experiments illustrate that we outperform the state-of-the-art unsupervised learning baselines by improving the performance more than 10% for ROUGE-1 and more than 50% for ROUGE-2 scores. Moreover, we achieve comparable results to recent end-to-end models. [ABSTRACT FROM AUTHOR]

Automatic text summarization is considered as an important task in various fields in natural language processing such as information retrieval. It is a process of automatically generating a text representation. Text summarization can be a solution to the problem of information overload. Hence, with the large amount of information available on the Internet, the presentation of a document by a summary helps to get the most relevant result of a search. We propose in this paper a new free Arabic structured corpus in the standard XML TREC format. ANT corpus v2.1 is collected using RSS feeds from different news sources. This corpus is useful for multiple text mining purposes such as generic text summarization, clustering or classification. We test this corpus for an unsupervised single-document extractive summarization using statistical and graph-based language-independent summarizers such as LexRank, TextRank, Luhn and LSA. We investigate the sensitivity of the summarization process to the stemming and stop words removal steps. We evaluate these summarizers performance by comparing the extracted texts fragments to the abstracts existing in ANT corpus v2.1 using ROUGE and BLEU metrics. Experimental results show that LexRank summarizer has achieved the best scores for the ROUGE metric using the stop words removal scenario. [ABSTRACT FROM AUTHOR]

At present, most Chinese text summarization algorithms use the sequence-to-sequence model, but this model is prone to the problems of unknown words and incomplete content generation. To address these problems, we propose a new two-stage automatic text summarization method using keyword information and adversarial learning in this paper. On the one hand, the proposed method integrates the keyword information into the sequence-to-sequence model. The main information and keywords of the article are considered simultaneously through the attention mechanism to improve the information of summary generation. On the other hand, adversarial learning is introduced into the proposed model to avoid the problem that the semantic vector after passing through the encoder cannot save the context information better. Experiments are carried out on the Chinese dataset LCSTS, and the comparison results show that the proposed method has advantages in abstractive summarization. [ABSTRACT FROM AUTHOR]

Abstractive text summarization using attentional recurrent neural network (sequence-to-sequence) models have proven to be very effective. In this paper, a novel hybrid approach is presented for generating abstractive text summaries by combining fuzzy logic rules (which selects extractive sentences) with bidirectional long short-term memory (Bi-LSTM) which further produces abstractive summary. Bi-LSTM uses attention mechanism and Adam optimizer for updating network weights. The proposed approach utilizes fuzzy measures and inference to extract textual information from the document to find the most relevant sentences. These relevant sentences are given as input to Bi-LSTM to produce an abstractive summary of the significant sentences. The proposed FLSTM model is evaluated using ROUGE toolkit. The experiment is performed on standard datasets (i.e., DUC and CNN/daily mail). Another salient feature of this work is merging of DUC 2003–2004, DUC 2006–2007 datasets to generate a larger dataset to achieve better results. The FLSTM model is compared with other state-of-the-art models, and the empirical results suggested that the proposed FLSTM model outperforms all other models. [ABSTRACT FROM AUTHOR]

The methods of Automatic Extractive Summarization (AES) uses the features of the sentences of the original text to extract the most important information that will be considered in summary. It is known that the first sentences of the text are more relevant than the rest of the text (this heuristic is called baseline), so the position of the sentence (in reverse order) is used to determine its relevance, which means that the last sentences have practically no possibility of being selected. In this paper, we present a way to soften the importance of sentences according to the position. The comprehensive tests were done on one of the best AES methods using the bag of words and n-grams models with the with DUC02 and DUC01 data sets to determine the importance of sentences. [ABSTRACT FROM AUTHOR]

Information Overload'is not a new term but with the massive development in technology which enables anytime, anywhere, easy and unlimited access; participation & publishing of information has consequently escalated its impact. Assisting users`informational searches with reduced reading surfing time by extracting and evaluating accurate, authentic & relevant information are the primary concerns in the present milieu. Automatic text summarization is the process of condensing an original document into shorter form to create smaller, compact version from the abundant information that is available, preserving the content & meaning such that it meets the needs of the user. Though many summarization techniques have been proposed but there are no `silver bullets'to achieve the superlative results as of human generated summaries. Thus, the domain of text summarization is an active and dynamic field of study, practice & research with the continuous need to expound novel techniques for achieving comparable & effectual results. Fuzzy logic has appeared as a powerful theoretical framework for studying human reasoning and its application has been explored within the domain of text summarization in the past few years. This paper is a systematic literature review to gather, analyze, and report the trends, gaps and prospects of using fuzzy logic for automatic text summarization on the basis of the findings in original studies. [ABSTRACT FROM AUTHOR]

This paper presents a comparative statistical analysis of the language features most commonly used for Automatic Text Summarization (ATS), namely: Parts of Speech (PoS) (unigrams and bigrams), sentiments (by token and sentence), and Rhetorical Structure Theory (RTS) relations. The analyses were carried out on both human-made and machine-made summaries, in order to determine whether current ATS systems capture the same kind of information as humans do. Our results show that there are some marked differences between machine and human-made summaries, which at times may seem counterintuitive. For instance, named entities were usually frequent in machine-made summaries, but not in human-made ones. Similarly, words perceived to hold a "neutral" sentiment were systematically favored by machines, but not always by humans. • This paper investigates pertinence of language features commonly utilized in ATS. • Statistical comparisons were conducted between human-made and machine-made summaries. • Some features were interestingly used moderately by humans, but not by machines. [ABSTRACT FROM AUTHOR]

Automatic text summarization technology has a very broad application prospect in many fields ? such as web search and browsing recommendation. The classic text summarization algorithm uses statistical methods to extract article keywords and topic sentences. It ignores semantic and grammatical information of the text to some extent. As distributed word vector embedding technology has been widely used in text summarization in recent years，we propose an automatic text summarization method based on word vector generation. This method mainly includes four modules： word vector generation，paragraph vector generation based on word vector，keyword extraction? and topic sentence extraction， through which an automatic text summarization of the document can finally be achieved. Experimental results show that the improved automatic text summarization method can extract topic sentences effectively. [ABSTRACT FROM AUTHOR]

In this paper, we present an extractive approach to document summarization based on Siamese Neural Networks. Specifically, we propose the use of Hierarchical Attention Networks to select the most relevant sentences of a text to make its summary. We train Siamese Neural Networks using document-summary pairs to determine whether the summary is appropriated for the document or not. By means of a sentence-level attention mechanism the most relevant sentences in the document can be identified. Hence, once the network is trained, it can be used to generate extractive summaries. The experimentation carried out using the CNN/DailyMail summarization corpus shows the adequacy of the proposal. In summary, we propose a novel end-to-end neural network to address extractive summarization as a binary classification problem which obtains promising results in-line with the state-of-the-art on the CNN/DailyMail corpus. [ABSTRACT FROM AUTHOR]

Highlights • The use of text summarization and fuzzy logic in automated text assessment. • The use of fuzzy logic summarization in Virtual Learning Environments. • A tool implemented as a prototype to evaluate the proposed method. • Experimental results showing improvements over existing methods. Abstract In the last two decades, the text summarization task has gained much importance because of the large amount of online data, and its potential to extract useful information and knowledge in a way that could be easily handled by humans and used for a myriad of purposes, including expert systems for text assessment. This paper presents an automatic process for text assessment that relies on fuzzy rules on a variety of extracted features to find the most important information in the assessed texts. The automatically produced summaries of these texts are compared with reference summaries created by domain experts. Differently from other proposals in the literature, our method summarizes text by investigating correlated features to reduce dimensionality, and consequently the number of fuzzy rules used for text summarization. Thus, the proposed approach for text summarization with a relatively small number of fuzzy rules can benefit development and use of future expert systems able to automatically assess writing. The proposed summarization method has been trained and tested in experiments using a dataset of Brazilian Portuguese texts provided by students in response to tasks assigned to them in a Virtual Learning Environment (VLE). The proposed approach was compared with other methods including a naive baseline, Score, Model and Sentence, using ROUGE measures. The results show that the proposal provides better f-measure (with 95% CI) than aforementioned methods. [ABSTRACT FROM AUTHOR]

The fast-growing amount of information on the Internet makes the research in automatic document summarization very urgent. It is an effective solution for information overload. Many approaches have been proposed based on different strategies, such as latent semantic analysis (LSA). However, LSA, when applied to document summarization, has some limitations which diminish its performance. In this work, we try to overcome these limitations by applying statistic and linear algebraic approaches combined with syntactic and semantic processing of text. First, the part of speech tagger is utilized to reduce the dimension of LSA. Then, the weight of the term in four adjacent sentences is added to the weighting schemes while calculating the input matrix to take into account the word order and the syntactic relations. In addition, a new LSA-based sentence selection algorithm is proposed, in which the term description is combined with sentence description for each topic which in turn makes the generated summary more informative and diverse. To ensure the effectiveness of the proposed LSA-based sentence selection algorithm, extensive experiment on Arabic and English are done. Four datasets are used to evaluate the new model, Linguistic Data Consortium (LDC) Arabic Newswire-a corpus, Essex Arabic Summaries Corpus (EASC), DUC2002, and Multilingual MSS 2015 dataset. Experimental results on the four datasets show the effectiveness of the proposed model on Arabic and English datasets. It performs comprehensively better compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Many researches have been converging on automatic text summarization as increasing of text documents due to the expansion of information diffusion constantly. The objective of this proposal is to achieve the most reliable and substantial context or most relevant brief summary of the text in extractive manner. The extractive text summarization produces the short summary of a certain text which contains the most important information of original text by extracting the set of sentences from the original document. This paper proposes an improved extractive text summarization method for documents by enhancing the conventional lexical chain method to produce better relevant information of the text using three distinct features or characteristics of keyword in a text. The keyword of the document is labeled using our previous work, transition probability distribution generator model which can learn the characteristics of the keyword in a document, and generates their probability distribution upon each feature. [ABSTRACT FROM AUTHOR]

The automatic evaluation of summaries is a hard task that continues to be open. The assessment aims to measure simultaneously the informativeness and readability of summaries. The scientific community has tackled this problem with partial solutions, in terms of informativeness, using ROUGE . However, to use this method, it is necessary to have multiple summaries made by humans (the references). Methods without human references have been implemented, but there are still far from being highly correlated to manual evaluations. In this paper we present SummTriver , an automatic evaluation method that tries to be more correlated to manual evaluation by using multiple divergences. The results are promising, especially for summarization campaigns. Besides this, we also present an interesting analysis, at micro-level, of how correlated the manual and automatic summaries evaluation methods are, when we make use of a large quantity of observations. [ABSTRACT FROM AUTHOR]

Automatically summarizing a document requires conveying the important points of a large document in only a few sentences. Extractive strategies for summarization are based on selecting the most important sentences from the input document(s). We claim here that standard features for estimating sentence importance can be effectively combined with innovative features that encode psychological aspects of communication. We employ Quantitative Text analysis tools for estimating psychological features and we inject them into state-of-the-art extractive summarizers. Our experiments demonstrate that this novel set of features is a good guidance for selecting salient sentences. Our empirical study concludes that psychological features are best suited for hard summarization cases. This motivated us to formally define and study the problem of predicting the difficulty of summarization. We propose a number of predictors to model the difficulty of every summarization problem and we evaluate several learning methods to perform this prediction task. [ABSTRACT FROM AUTHOR]

The volume of text data has been growing exponentially in the last years, mainly due to the Internet. Automatic Text Summarization has emerged as an alternative to help users find relevant information in the content of one or more documents. This paper presents a comparative analysis of eighteen shallow sentence scoring techniques to compute the importance of a sentence in the context of extractive single- and multi-document summarization. Several experiments were made to assess the performance of such techniques individually and applying different combination strategies. The most traditional benchmark on the news domain demonstrates the feasibility of combining such techniques, in most cases outperforming the results obtained by isolated techniques. Combinations that perform competitively with the state-of-the-art systems were found. [ABSTRACT FROM AUTHOR]

We assess the performance of generic text summarization algorithms applied to films and documentaries, using extracts from news articles produced by reference models of extractive summarization. We use three datasets: (i) news articles, (ii) film scripts and subtitles, and (iii) documentary subtitles. Standard ROUGE metrics are used for comparing generated summaries against news abstracts, plot summaries, and synopses. We show that the best performing algorithms are LSA, for news articles and documentaries, and LexRank and Support Sets, for films. Despite the different nature of films and documentaries, their relative behavior is in accordance with that obtained for news articles. [ABSTRACT FROM AUTHOR]

Automatic Text Summarization (ATS) is an essential field in natural language processing that attempts to condense large text documents so that users can assimilate information quickly. It finds uses in medical document summarization, review generation, and opinion mining. This work investigated an unsupervised extractive summarization approach that combined clustering with topic modeling to reduce topic bias. Latent Dirichlet Allocation was used for topic modeling, while K-Medoids clustering was employed for summary generation. The approach was evaluated on three datasets—Wikihow, CNN/DailyMail, and the DUC2002 Corpus. The Recall Oriented-Understudy for Gisting Evaluation (ROUGE) metrics were used for comparative analysis against recently reported techniques, specifically ROUGE-1 (R-1), ROUGE-2 (R-2), and ROUGE-L (R-L). The suggested framework offered scores of 34.80%, 9.13%, and 32.30% on the Wikihow Dataset, 43.90%, 19.01%, and 41.50% on the CNN/DailyMail Dataset, and 49.35%, 31.53%, and 41.72% on the DUC2002 Corpus (R-1, R-2, R-L respectively). These reported metrics are found to be superior when compared to similar recent works. Further, execution time of the proposed method was also recorded and compared with counterparts, which established its superior speed. Based on these promising outcomes, it was concluded that an unsupervised extractive summarization approach with greater subtopic focus significantly improves over generic topic modeling semantic and deep learning approaches. [ABSTRACT FROM AUTHOR]

Research in the area of automatic text summarization has intensified in recent years due to the large amount of information available in electronic documents. This article present the most relevant methods for automatic text extractive summarization that have been developed both for a single document and multiple documents, with special emphasis on methods based on algebraic reduction, clustering and evolutionary models, of which there is great amount of research in recent years, since they are language-independent and unsupervised methods. [ABSTRACT FROM AUTHOR]

Abstract: Automatic text summarization is an essential tool in this era of information overloading. In this paper we present an automatic extractive Arabic text summarization system where the user can cap the size of the final summary. It is a direct system where no machine learning is involved. We use a two pass algorithm where in pass one, we produce a primary summary using Rhetorical Structure Theory (RST); this is followed by the second pass where we assign a score to each of the sentences in the primary summary. These scores will help us in generating the final summary. For the final output, sentences are selected with an objective of maximizing the overall score of the summary whose size should not exceed the user selected limit. We used Rouge to evaluate our system generated summaries of various lengths against those done by a (human) news editorial professional. Experiments on sample texts show our system to outperform some of the existing Arabic summarization systems including those that require machine learning. [Copyright &y& Elsevier]

• An on-line extractive multi-source summarization algorithm. • Suitable to synthesize topic-related documents. • Produces highly readable summaries, while preserving topic information. • Language agnostic, shown to work in both English and Spanish sources. • Efficient, with execution times strictly below O (n 2). Web search users are likely to face problems related to the availability of large amounts of data. As the quantity of online content grows, the risk of missing relevant information during search can only increase. Moreover, external variables such as the users' reading proficiency level can further complicate the task. This article proposes an online multi-document summarization algorithm for text readability, as a means to simplify web search. The algorithm is designed to work over collections of topic-related documents, such as the ones returned as the results to a web query. Contrary to most modern approaches, no preliminary training for the algorithm is required. The algorithm was tested in both English and Spanish language documents, using different metrics of term and sentence relevance. The results were compared against summaries created by both human summarizers and third-party Automatic Text Summarization (ATS) systems in terms of two variables: readability and information content. In both variables, the results show generalized gains with respect to both the human summarizers and the third-party ATS systems. Furthermore, the algorithm achieved these results with a time complexity strictly lower than O (n 2) ; well below traditional machine learning approaches. [ABSTRACT FROM AUTHOR]

• Classifications and applications of text summarization systems are demonstrated. • Automatic text summarization approaches and their methods are illustrated. • Techniques (building blocks) to implement text summarization systems are exhibited. • Standard datasets and text summarization evaluation methods are explored. • Future research directions for automatic text summarization are presented. Automatic Text Summarization (ATS) is becoming much more important because of the huge amount of textual content that grows exponentially on the Internet and the various archives of news articles, scientific papers, legal documents, etc. Manual text summarization consumes a lot of time, effort, cost, and even becomes impractical with the gigantic amount of textual content. Researchers have been trying to improve ATS techniques since the 1950s. ATS approaches are either extractive, abstractive, or hybrid. The extractive approach selects the most important sentences in the input document(s) then concatenates them to form the summary. The abstractive approach represents the input document(s) in an intermediate representation then generates the summary with sentences that are different than the original sentences. The hybrid approach combines both the extractive and abstractive approaches. Despite all the proposed methods, the generated summaries are still far away from the human-generated summaries. Most researches focus on the extractive approach. It is required to focus more on the abstractive and hybrid approaches. This research provides a comprehensive survey for the researchers by presenting the different aspects of ATS: approaches, methods, building blocks, techniques, datasets, evaluation methods, and future research directions. [ABSTRACT FROM AUTHOR]

Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. However, there is still no guarantee that the generated summaries are grammatical, concise, and convey all salient information as the original documents have. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model, and domain knowledge concern for ATS. This architecture mainly contains three components: domain knowledge base construction based on representation learning, the attentional encoder–decoder model for rhetorical parsing, and subroutine-based model for text summarization. Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived. In the unsupervised rhetorical parsing module, the idea of translation was adopted to alleviate the problem of data scarcity. The subroutine-based summarization model purely depends on the derived rhetorical structure trees and can generate content-balanced results. To evaluate the summary results without golden standard, we proposed an unsupervised evaluation metric, whose hyper-parameters were tuned by supervised learning. Experimental results show that, on a large-scale Chinese dataset, our proposed approach can obtain comparable performances compared with existing methods. • Knowledge-guided unsupervised rhetorical parsing. • A domain knowledge base construction approach based on representation learning. • Subroutine-based text summarization model. • An unsupervised evaluation metric for text summarization. [ABSTRACT FROM AUTHOR]