Text Summarization Approach Research Articles

Frequency-Driven Approach for Extractive Text Summarization

Due to Digital Revolution, most books and newspaper articles are now available online. Particularly for kids and students, prolonged screen time might be bad for eyesight and attention span. As a result, summarizing algorithms are required to provide long web content in an easily digestible style. The proposed methodology is using term frequency and inverse document frequency driven model, in which the document summary is generated based on each word in a corpus. According to the preferred method, each sentence is rated according to its tf-idf score, and the document summary is produced in a fixed ratio to the original text. Expert summaries froma data set are used for measuring precision and recall using the proposed approach’s ROUGE model. towards the development of such a framework is presented.

ANALSYING THE PARALLEL FUSION LOGIC AND FUSION K-MEANS (FKM) WITH LANGUAGE DOCUMENT

Text summarization is a method of retrieving information, and it is very effective. Text summarization approach techniques fall into two categories: abstract and abstract. This white paper focuses on extraction techniques so that the output of the application is the key sentence taken verbatim from the original text without verbal modification. There are four main processes in this research. These are the preprocessing phase, the scoring function, the optimization of summarization by two methods (logic and fused K-Means), and the extraction of summarization results. In this study, seven features are used to calculate a score for each sentence. The core of this study is to compare the reliability of fused logic and fused k-means methods in optimizing the aggregation results process. The results showed that the Fusion Logic method outperformed the Fusion K-Means method and had the highest similarity to human summarization, with a percentage accuracy of 48.25% for Fusion Logic and 44% for Fusion K-Means. It was %.33%. Accuracy improves with the additional compression of 0.67% for Fusion Logic Method and 3.5% for Fusion K-Means. Keywords: Language, Text Features, Scores Sentences, Fusion Logic, Fusion K–Means

OCR-based Hybrid Image Text Summarizer using Luhn Algorithm with FinetuneTransformer Modelsfor Long Document

The accessibility of an enormous number of image text documents on the internet has expanded the opportunities to develop a system for image text recognition with text summarization. Several approaches used in ATS in the literature are based on extractive and abstractive techniques; however, few implementations of the hybrid approach were observed. This paper employed state-of-the-art transformer models with the Luhn algorithm for extracted texts using Tesseract OCR. Nine models were generated and tested using the hybrid text summarization approach. Using ROUGE metrics, we compared the proposed system finetune abstractive models against existing abstractive models that use the same dataset Xsum. As a result, the finetune model got the highest ROUGE score during evaluation; in ROUGE-1 score was 57%, the ROUGE-2 score was 43%, and the ROUGE-L score was 42%. Furthermore, even when better algorithms and models were available for summarization, the Luhn algorithm and T5 finetune model provided significant results.

Extractive Article Summarization Using Integrated TextRank and BM25+ Algorithm

The quantity of textual data on the internet is growing exponentially, and it is very tough task to obtain important and relevant information from it. An efficient and effective method is required that provides a concise summary of an article. This can be achieved by the usage of automatic text summarization. In this research, the authors suggested an efficient approach for text summarization where an extractive summary is generated from an article. The methodology was modified by integrating a normalized similarity matrix of both BM25+ and conventional TextRank algorithm, which resulted in the improvised results. A graph is generated by taking the sentences in the article as nodes and edge weights as the similarity score between two sentences. The maximum rank nodes are selected, and the summary is extracted. Empirical evaluation of the proposed methodology was analyzed and compared with baseline methods viz. the conventional TextRank algorithm, term frequency–inverse document frequency (TF–IDF) cosine, longest common consequence (LCS), and BM25+ by taking precision, recall, and F1 score as evaluation criteria. ROUGE-1, ROUGE-2, and ROUGE-L scores were calculated for all the methods. The outcomes demonstrate that the proposed method can efficiently summarize any article irrespective of the category it belongs to.

Multi-Encoder Transformer for Korean Abstractive Text Summarization

In this paper, we propose a Korean abstractive text summarization approach that uses a multi -encoder transformer. Recently, in many natural language processing (NLP) tasks, the use of the pre-trained language models (PLMs) for transfer learning has achieved remarkable performance. In particular, transformer-based models such as Bidirectional Encoder Representations from Transformers (BERT) are used for pre-training and applied to downstream tasks, showing state-of-the-art performance including abstractive text summarization. However, existing text summarization models usually use one pre-trained model per model architecture, meaning that it becomes necessary to choose one PLM at a time. For PLMs applicable to Korean abstractive text summarization, there are publicly available BERT-based pre-trained Korean models that offer different advantages such as Multilingual BERT, KoBERT, HanBERT, and KorBERT. We assume that if these PLMs could be leveraged simultaneously, better performance would be obtained. We propose a model that uses multiple encoders which are capable of leveraging multiple pre-trained models to create an abstractive summary. We evaluate our method using three benchmark Korean abstractive summarization datasets, each named Law (AI-Hub), News (AI-Hub), and News (NIKL) datasets. Experimental results show that the proposed multi-encoder model variations outperform single -encoder models. We find the empirically best summarization model by determining the optimal input combination when leveraging multiple PLMs with the multi-encoder method.

A Hybrid Approach for Text Summarization Using Social Mimic Optimization Algorithm

A Hybrid Approach for Text Summarization Using Social Mimic Optimization Algorithm

Text Summarization Using Deep Learning

In the big data era, there has been an explosion in the amount of text data from a variety of sources. This volume of text is an inestimable source of information and knowledge which needs to be effectively summarized to be useful. There are plenty of text material available on the internet. Earlier traditional approaches for extractive text summarization have been heavily dependent on human engineered features. However, it is a laborious and tedious task. In this paper, a data-driven approach has been used to generate extractive summaries using deep learning. So there is a problem of searching for relevant documents from the number of documents available, and absorbing relevant information from it. Thus, the need for a solution emerges, that transforms this vast raw information into useful data which a human brain can understand. One such common technique in research that helps in dealing with enormous data is text summarization. We must first comprehend what a summary is before moving on to text summarization. A summary is a text created from one or more texts that delivers key information from the source material in a condensed style. The most significant benefit of adopting a summary is that it cuts down on reading time. Text summarization is the process of extracting the most important meaningful information from a document or set of related documents and compressing it into a shorter version while retaining its overall meanings. Automatic summary is a well-known method for refining a document's important points. It works by providing a reduced version of the text that preserves significant information. There are two types of text summarization methods: Extractive and Abstractive.

Comparative Analysis of Automated Text Summarization Techniques: The Case of Ethiopian Languages

Nowadays, there is an abundance of information available from both online and offline sources. For a single topic, we can get more than hundreds of sources containing a wealth of information. The ability to extract or generate a summary of popular content allows users to quickly search for content and obtain preliminary data in the shortest amount of time. Manually extracting useful information from them is a difficult task. Automatic text summarization (ATS) systems are being developed to address this issue. Text summarization is the process of extracting useful information from large documents and compressing it into a summary while retaining all the relevant contents. This review paper provides a broad overview of ATS research works in various Ethiopian languages such as Amharic, Afan Oromo, and Tigrinya using different text summarization approaches. The work has identified the novel and recommended state-of-the-art techniques and methods for future researchers in the area and provides knowledge and useful support to new researchers in this field by providing a concise overview of the various feature extraction methods and classification techniques required for different types of ATS approaches applied to the Ethiopian languages. Finally, different recommendations for future researchers have been forwarded.

DeepSumm: Exploiting topic models and sequence to sequence networks for extractive text summarization

In this paper, we propose DeepSumm, a novel method based on topic modeling and word embeddings for the extractive summarization of single documents. Recent summarization methods based on sequence networks fail to capture the long range semantics of the document which are encapsulated in the topic vectors of the document. In DeepSumm, our aim is to utilize the latent information in the document estimated via topic vectors and sequence networks to improve the quality and accuracy of the summarized text. Each sentence is encoded through two different recurrent neural networks based on probabilistic topic distributions and word embeddings, and then a sequence to sequence network is applied to each sentence encoding. The outputs of the encoder and the decoder in the sequence to sequence networks are combined after weighting using an attention mechanism and converted into a score through a multi-layer perceptron network. We refer to the score obtained through the topic model as Sentence Topic Score (STS) and to the score generated through word embeddings as Sentence Content Score (SCS). In addition, we propose Sentence Novelty Score (SNS) and Sentence Position Score (SPS) and perform a weighted fusion of the four scores for each sentence in the document to compute a Final Sentence Score (FSS). The proposed DeepSumm framework was evaluated on the standard DUC 2002 benchmark and CNN/DailyMail datasets. Experimentally, it was demonstrated that our method captures both the global and the local semantic information of the document and essentially outperforms existing state-of-the-art approaches for extractive text summarization with ROUGE-1, ROUGE-2, and ROUGE-L scores of 53.2, 28.7 and 49.2 on DUC 2002 and 43.3, 19.0 and 38.9 on CNN/DailyMail dataset.

Semi-Extractive Text Summarization Approach to Extract Research Objective of Academic Literature

Semi-Extractive Text Summarization Approach to Extract Research Objective of Academic Literature

XAI-Based Reinforcement Learning Approach for Text Summarization of Social IoT-Based Content

The purpose of automatic text summarising technology is to condense a given text while properly portraying the main information in the original text in a summary. To present generative text summarising approaches, on the other hand, restructure the original language and introduce new words when constructing summary sentences, which can easily lead to incoherence and poor readability. This research proposes a XAI (explainable artificial intelligence)-based Reinforcement Learning-based Text Summarization of Social IoT-Based Content using Reinforcement Learning. Furthermore, standard supervised training based on labelled data to improve the coherence of summary sentences has substantial data costs, which restricts practical applications. In order to do this, a ground-truth-dependent text summarization (generation) model (XAI-RL) is presented for coherence augmentation. On the one hand, based on the encoding result of the original text, a sentence extraction identifier is generated, and the screening process of the vital information of the original text is described. Following the establishment of the overall benefits of the two types of abstract writings, the self-judgment approach gradient assists the model in learning crucial sentence selection and decoding the selected key phrases, resulting in a summary text with high sentence coherence and good content quality. Experiments show that the proposed model's summary content index surpasses text summarising ways overall, even when there is no pre-annotated summary ground-truth; information redundancy, lexical originality, and abstract perplexity also outperform the current methods.

Improving the performance of semantic graph-based keyword extraction and text summarization using fuzzy relations in Hindi Wordnet

In this study, a Fuzzy Semantic Graph-based approach is proposed to extract keywords and generate extractive text summaries from Hindi text documents. Hindi Wordnet is used as a knowledge source to construct the semantic graph. As the semantic relations defined in Hindi Wordnet are crisp, they do not capture the semantic relationship as a matter of degree. Due to that, many terms are represented as not being related, while these can share some meaningful relationship as per real-life scenarios. To overcome this curb of Hindi Wordnet, the paper presents several fuzzy semantic associations between such terms by assigning a value ranging from 0 to 1 to such relations. While constructing the semantic graph to represent documents using Hindi Wordnet semantic relations, the terms sharing fuzzy semantic relations are also added to enhance the quality of the graph. The experiments are done to extract potential keywords and to generate a good content summary. It is observed that such semantics generate a more accurate summary and produce prospective keywords for the document. The performance of the proposed approach fuzzy-based semantic graph is compared to semantic graph-based approach for keyword extraction and text summarization. The keywords extracted and the summary generated by the proposed approach is match up to human extracted keywords and human-generated text summary. The proposed approach results are evaluated using precision, recall, and f-measure. Different outcomes of generated text summaries are evaluated using the ROUGE matrix. The results of the proposed approach are pretty encouraging.

A text summary-based method to detect new events from streams of online news articles

New event detection (NED), which is crucial to firms’ environmental surveillance, requires timely access to and effective analysis of live streams of news articles from various online sources. These news articles, available in unprecedent frequency and quantity, are difficult to sift through manually. Most of existing techniques for NED are full-text-based; typically, they perform full-text analysis to measure the similarity between a new article and previous articles. This full-text-based approach is potentially ineffective, because a news article often contains sentences that are less relevant to define the focal event being reported and the inclusion of these less relevant sentences into the similarity estimation can impair the effectiveness of NED. To address the limitation of the full-text-based approach and support NED more effectively and efficiently, this study proposes and develops a summary-based event detection method that first selects relevant sentences of each article as a summary, then uses the resulting summaries to detect new events. We empirically evaluate our proposed method in comparison with some prevalent full-text-based techniques, including a vector space model and two deep-learning-based models. Our evaluation results confirm that the proposed method provides greater utilities for detecting new events from online news articles. This study demonstrates the value and feasibility of the text summarization approach for generating news article summaries for detecting new events from live streams of online news articles, proposes a new method more effective and efficient than the benchmark techniques, and contributes to NED research in several important ways.

Attention based Recurrent Neural Network for Nepali Text Summarization

Automatic text summarization has been a challenging topic in natural language processing (NLP) as it demands preserving important information while summarizing the large text into a summary. Extractive and abstractive text summarization are widely investigated approaches for text summarization. In extractive summarization, the important sentence from the large text is extracted and combined to create a summary whereas abstractive summarization creates a summary that is more focused on meaning, rather than content. Therefore, abstractive summarization gained more attention from researchers in the recent past. However, text summarization is still an untouched topic in the Nepali language. To this end, we proposed an abstractive text summarization for Nepali text. Here, we, first, create a Nepali text dataset by scraping Nepali news from the online news portals. Second, we design a deep learning-based text summarization model based on an encoder-decoder recurrent neural network with attention. More precisely, Long Short-Term Memory (LSTM) cells are used in the encoder and decoder layer. Third, we build nine different models by selecting various hyper-parameters such as the number of hidden layers and the number of nodes. Finally, we report the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) score for each model to evaluate their performance. Among nine different models created by adjusting different numbers of layers and hidden states, the model with a single-layer encoder and 256 hidden states outperformed all other models with F-Score values of 15.74, 3.29, and 15.21 for ROUGE-1 ROUGE-2 and ROUGE-L, respectively.

An Automatic Abstractive Text Summarization System

Abstractive text summarization is one of the most interesting problems in the research field of Natural Language Processing. Recent advances in sequence to sequence model have made it possible to apply new approaches for abstractive text summarization and perform significantly. But most of the existing systems suffer from some drawbacks like word repetition, producing inaccurate or irrelevant information etc. In this work we propose a novel architecture incorporating advanced word embedding layer and topical feature with a pointer generator network to generate more topic oriented summaries in a logically sequenced way. Adding a word embedding layer with the model can capture semantic features of words in the input sequence more accurately. Also our proposed system with incorporated topical features ensures that the summaries focus on the most important parts of the source document. We applied our model to the CNN/Daily Mail dataset and outperformed the baseline model by all the ROUGE scores. DUJASE Vol. 6 (2) 39-48, 2021 (July)

Extractive Text Summarization for Wolaita

Text summarization is the mechanism of summarizing a huge document comprising vast amount of information which is difficult to overcome and understand its message easily in any written documents for whatever languages without losing its entire message. A short and precise document which conveys intended information for the user in demand is expected in this information age. In addition to that, summarizing a document with vast amount of information is very difficult and time consuming specially for less resourced and technologically unfavored languages. Therefore in this study, the researcher proposed to address such problems for Wolaita by using graph based extractive text summarization approach. To attain the goal of this study the researcher prepared 92 documents for the study, explored extractive text summarization with graph-based approach to address the problems, performed text preprocessing tasks and finally developed text summarization model by using TextRank algorithms. The researcher used 92 documents, performed 92 various experiments, on documents and experimental results and findings were discussed in detail. To evaluate the model performance, three different expert summaries were collected for documents and computed system generated summaries with ROUGE evaluation metric. The researcher justified it with ROUGE evaluation metrics by comparing the system summaries with the expert summaries. The result obtained from the experiment shows promising result in summarization of Wolaita text. Finally, the experimental result of a 61.16% recall, 60.69% precision and 60.46% f-measures were obtained.

A Novel Approach for Semantic Extractive Text Summarization

Text summarization is a technique for shortening down or exacting a long text or document. It becomes critical when someone needs a quick and accurate summary of very long content. Manual text summarization can be expensive and time-consuming. While summarizing, some important content, such as information, concepts, and features of the document, can be lost; therefore, the retention ratio, which contains informative sentences, is lost, and if more information is added, then lengthy texts can be produced, increasing the compression ratio. Therefore, there is a tradeoff between two ratios (compression and retention). The model preserves or collects all the informative sentences by taking only the long sentences and removing the short sentences with less of a compression ratio. It tries to balance the retention ratio by avoiding text redundancies and also filters irrelevant information from the text by removing outliers. It generates sentences in chronological order as the sentences are mentioned in the original document. It also uses a heuristic approach for selecting the best cluster or group, which contains more meaningful sentences that are present in the topmost sentences of the summary. Our proposed model extractive summarizer overcomes these deficiencies and tries to balance between compression and retention ratios.

Extractive summarization of Malayalam documents using latent Dirichlet allocation: An experience

Abstract Automatic text summarization (ATS) extracts information from a source text and presents it to the user in a condensed form while preserving its primary content. Many text summarization approaches have been investigated in the literature for highly resourced languages. At the same time, ATS is a complicated and challenging task for under-resourced languages like Malayalam. The lack of a standard corpus and enough processing tools are challenges when it comes to language processing. In the absence of a standard corpus, we have developed a dataset consisting of Malayalam news articles. This article proposes an extractive topic modeling-based multi-document text summarization approach for Malayalam news documents. We first cluster the contents based on latent topics identified using the latent Dirichlet allocation topic modeling technique. Then by adopting vector space model, the topic vector and sentence vector of the given document are generated. According to the relevant status value, sentences are ranked between the document’s topic and sentence vectors. The summary obtained is optimized for non-redundancy. Evaluation results on Malayalam news articles show that the summary generated by the proposed method is closer to the human-generated summaries than the existing text summarization methods.

RankSum—An unsupervised extractive text summarization based on rank fusion

In this paper, we propose Ranksum, an approach for extractive text summarization of single documents based on the rank fusion of four multi-dimensional sentence features extracted for each sentence: topic information, semantic content, significant keywords, and position. The Ranksum obtains the sentence saliency rankings corresponding to each feature in an unsupervised way followed by the weighted fusion of the four scores to rank the sentences according to their significance. The scores are generated in completely unsupervised way, and a labeled document set is required to learn the fusion weights. Since we found that the fusion weights can generalize to other datasets, we consider the Ranksum as an unsupervised approach. To determine topic rank, we employ probabilistic topic models whereas semantic information is captured using sentence embeddings. To derive rankings using sentence embeddings, we utilize Siamese networks to produce abstractive sentence representation and then we formulate a novel strategy to arrange them in their order of importance. A graph-based strategy is applied to find the significant keywords and related sentence rankings in the document. We also formulate a sentence novelty measure based on bigrams, trigrams, and sentence embeddings to eliminate redundant sentences from the summary. The ranks of all the sentences – computed for each feature – are finally fused to get the final score for each sentence in the document. We evaluate our approach on publicly available summarization datasets — CNN/DailyMail and DUC 2002. Experimental results show that our approach outperforms other existing state-of-the-art summarization methods.

An approach for extractive text summarization using fuzzy evolutionary and clustering algorithms

Automatic text summarization schemes are indeed helpful for glancing briefly at the text document. With this motivation, we introduce here a two-stage hybrid model for text summarization task by utilizing the strength of various approaches. In the first step, we cluster the sentences of a document according to their similarity using a partitional clustering algorithm. We then use a linear combination of the normalized Google distance and word mover’s distance to differentiate two sentences. The notion of gap statistics is exploited to approximate the number of partitions for the given document needed in the partitional clustering algorithm. We extract the significant sentences from each cluster (partition), which are recognized by their adjusted text feature scores, in the second step. The teaching–learning based optimization approach is used to find the optimal weights for the text features whereas a fuzzy inference system with a full-fledged knowledge base generated by humans is employed to determine the final score of the sentences. Moreover, we have also proposed an exact method to give a solution for the summarization problem by modeling it as an Integer Linear Programming (ILP) problem. We evaluate the proposed methods on three different datasets: DUC 2001, DUC 2002, and CNN. The observed results on these standard datasets manifest the efficacy of the proposed methods. We further show that partitioning a document in an optimal number of clusters plays a major role in content coverage in summaries. The performance of the proposed hybrid method shows that the combination of fuzzy, evolutionary, and clustering algorithms produces good summaries of the documents.