A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization

In this era of growing digital media, the volume of text data increases day by day from various sources and may contain entire documents, books, articles, etc. This amount of text is a source of information that may be insignificant, redundant, and sometimes may not carry any meaningful representation. Therefore, we require some techniques and tools that can automatically summarize the enormous amounts of text data and help us to decide whether they are useful or not. Text summarization is a process that generates a brief version of the document in the form of a meaningful summary. It can be classified into abstractive text summarization and extractive text summarization. Abstractive text summarization generates an abstract type of summary from the given document. In extractive text summarization, a summary is created from the given document that contains crucial sentences of the document. Many authors proposed various techniques for both types of text summarization. This paper presents a survey of extractive text summarization on graphical-based techniques. Specifically, it focuses on unsupervised and supervised techniques. This paper shows the recent works and advances on them and focuses on the strength and weaknesses of surveys of previous works in tabular form. At last, it concentrates on the evaluation measure techniques of summary.

Increased availability of the Internet and social media has created another ‘world of data’ comprised of text, audio and video files. It is very difficult for a user to get the accurate summary or to comprehend the relevant and important items from the available media. Additionally, readers or evaluators of these data files are interested only in the relevant content or summary to be retrieved in the less duration from the source files. Automatic text summarization (ATS) is the only way to summarize single or multiple documents to obtain relevant content from the source files. Available ATS systems generate bad summaries and take a lot of time and space for long documents due to inaccurate encoding. Therefore, in this work, we have introduced an approach for extractive text summarization using sentence ranking. Experiments have been performed over BBC and CNN news datasets and evaluated in terms of ROUGE using N-gram Language Model. The quantitative values of the metrics show the effectiveness of the proposed approach for news datasets.

Text summarization is the process of creating a short, accurate and fluent summary of a longer text document. As plenty of digital data is available online, automatic text summarization methods greatly needed to help and understand the lengthy & complex documents quickly by discovering the relevant information. This paper proposes the text summarization method for short news articles and long scientific papers using unsupervised neural network model. The proposed method works in four main steps: input document pre-processing, feature extraction, feature enhancement and final summary generation. We have extracted combination of various statistical and linguistic features from input document, which helps in improving the quality of sentence selection. Further Restricted Boltzmann Machine (RBM) model is used to capture & enhance the discriminative, abstract features in an unsupervised way to improve the overall performance without losing any significant information. Sentences are scored based on enhanced feature set and top sentences are selected for final extractive summary. Performance of the proposed method is evaluated using Rouge score and compared with TextRank, LexRank, LSA & Luhn baseline methods and the results demonstrates that proposed methodology performs better compared to other methods.

Graph neural networks (GNNs) typically exhibit superior performance in shallow architectures. However, as the network depth increases, issues such as overfitting and oversmoothing of hidden vector representations arise, significantly diminishing model performance. To address these challenges, this paper proposes a Two-Channel Classification Algorithm Based on Graph Attention Network (TCC_GAT). Initially, nodes exhibiting similar interaction behaviors are identified through cosine similarity, thereby enhancing the foundational graph structure. Subsequently, an attention mechanism is employed to adaptively integrate neighborhood information within the enhanced graph structure, with a multi-head attention mechanism applied to mitigate overfitting. Furthermore, the K-nearest neighbors algorithm is adopted to reconstruct the basic graph structure, facilitating the learning of structural information and neighborhood features that are challenging to capture on interaction graphs. This approach addresses the difficulties associated with learning high-order neighborhood information. Finally, the embedding representations of identical nodes across different graph structures are fused to optimize model classification performance, significantly enhancing node embedding representations and effectively alleviating the over-smoothing issue. Semi-supervised experiments and ablation studies conducted on the Cora, Citeseer, and Pubmed datasets reveal an accuracy improvement ranging from 1.4% to 4.5% compared to existing node classification algorithms. The experimental outcomes demonstrate that the proposed TCC_GAT achieves superior classification results in node classification tasks.

With the rapid growth of digital content, there is a need for an automatic text summarizer to provide short text from a long text document. Many research works have been presented for extractive text summarization (ETS). This article mainly focuses on the graph-based ETS approach for multiple Telugu text documents. A modified Text-Rank algorithm is employed with the noun and verb count of each sentence in the text as the initial score of each node. To get the optimal features, a novel feature selection algorithm called improved Flamingo Search Algorithm is proposed in this article. Though graph-based ETS is an important approach, the generated summaries are redundant. To reduce the redundancy in the generated summary, maximum marginal relevance is combined with the modified Text-Rank. Different word-embedding techniques such as Fast-Text, Word2vec, TF-IDF, and one-hot encoding are utilized to experiment with the proposed approach. The performance of the proposed text summarization approach is evaluated with BLEU and ROUGE in terms of F-measure, precision, and recall.

The method of reducing information from an original text document while maintaining the vital information is known as text summarizing. The amount of text data available has increased dramatically in recent years from a variety of sources. A large volume of text is an excellent source of information and knowledge of the source is essential for efficiently summarizing information that must be useful. Summarization facilitates the acquisition of vital and required information in a short period of time. Text summarization is required in a variety of domains, including news article summaries, email summaries and information summaries in the medical profession to track a patient's medical history for future treatment and so on. In summarization, there are two methods: extractive summarization and abstractive summarization. In this work, extractive summarization is used on the COVID-19 dataset. Different models and their results have been discussed.

Recommendation systems is the core of most online experiences, guiding people to the right products, films, music, courses, and even social links when the choices are overwhelming. They work by learning from large interaction logs and applying predictive models to surface content that fits each user’s tastes, steadily improving as algorithms and data grow richer. As AI and deep learning have developed, classic strategies like collaborative filtering and content-based filtering are increasingly paired with, or superseded by, neural architectures that can model more nuanced patterns in behaviour and content. Among these neural approaches, graph neural networks—and especially Graph Attention Networks (GATs)—have become influential for recommendation because they treat users and items as nodes in a graph and learn from the connections between them. With attention mechanisms, GATs decide which neighbours matter most for a given prediction, amplifying useful signals and dampening noise to learn stronger user and item representations. This survey traces how the industry moved from traditional methods to graph-based models centred on GATs, comparing approaches on scalability, ranking accuracy, data sparsity, and interpretability across widely used benchmarks. Drawing from recent peer‑reviewed work, it highlights architectures and training practices that consistently help in real-world settings, as well as gaps that still limit robust deployment at scale. Looking forward, several directions stand out: using explainable AI to clarify why specific items are recommended, combining reinforcement learning with GATs for adaptive policies, and adopting federated learning to protect user privacy while training on distributed data. The versatility of GAT-based recommenders is already visible across domains—from e‑commerce and online learning to healthcare and social feeds—where graph structure and selective attention naturally fit the data. Overall, the evidence points to GATs as a key ingredient for the next generation of personalized, context‑aware, and trustworthy recommendation systems. Keywords: Recommendation Systems, Collaborative Filtering, Graph Neural Networks, Graph Attention Networks

Text summarization is the process of creating a shorter version of one or more text documents. Automatic text summarization has become an important way of finding relevant information in large text libraries or in the Internet. Extractive text summarization techniques select entire sentences from documents according to some criteria to form a summary. Sentence scoring is the technique most used for extractive text summarization, today. Depending on the context, however, some techniques may yield better results than some others. This paper advocates the thesis that the quality of the summary obtained with combinations of sentence scoring methods depend on text subject. Such hypothesis is evaluated using three different contexts: news, blogs and articles. The results obtained show the validity of the hypothesis formulated and point at which techniques are more effective in each of those contexts studied.

Recently, automation is considered vital in most fields since computing methods have a significant role in facilitating work such as automatic text summarization. However, most of the computing methods that are used in real systems are based on graph models, which are characterized by their simplicity and stability. Thus, this paper proposes an improved extractive text summarization algorithm based on both topic and graph models. The methodology of this work consists of two stages. First, the well-known TextRank algorithm is analyzed and its shortcomings are investigated. Then, an improved method is proposed with a new computational model of sentence weights. The experimental results were carried out on standard DUC2004 and DUC2006 datasets and compared to four text summarization methods. Finally, through experiments on the DUC2004 and DUC2006 datasets, our proposed improved graph model algorithm TG-SMR (Topic Graph-Summarizer) is compared to other text summarization systems. The experimental results prove that the proposed TG-SMR algorithm achieves higher ROUGE scores. It is foreseen that the TG-SMR algorithm will open a new horizon that concerns the performance of ROUGE evaluation indicators.

Text summarization is referred to the process of rewriting a particular content into its brief version by understanding it. It is a serious need to obtain concise and relevant information from huge information. Automatic text summarization is fast-growing research area in natural language processing from last few years. It has improved from simple heuristics to neural network-based text summarization techniques. The extractive and abstractive text summarization generate the condensed text which saves time in reading the entire document. The abstractive approach is more complex as it needs natural language processing and neural network. Due to the availability of huge unsupervised data, traditional approach fails to provide accuracy in text summarization. The deep learning-based text summarization model gives a good performance as compared to the conventional techniques. In this paper, we have reviewed the recent work on text summarization based on deep learning techniques.

Automatic text summarization is a growing area of natural language processing research. Using extractive text summarization approach a concise summary of the input information sources is developed by selecting phrases and sentences on a given selection criterion that can be based on features e.g. syntactic, semantic, temporal, positional, etc. Text summarization for under resourced languages e.g. Urdu is even more challenging, due to the limited availability of basic computational resources to effectively extract textual features. Surmounting these challenges, this paper presents an extractive text summarization methodology for Urdu language documents based on sentence weight algorithm using segmentation, tokenization and stopwords as prominent features. ROUGE metric is used for system evaluation by comparing system generated and human generated summaries. System accuracy at Unigram, bigram and trigram level is 67 percent.

Extractive summarization of clinical trial descriptions

The paper describes a convex optimization formulation of the extractive text summarization problem and a simple and scalable algorithm to solve it. The optimization program is constructed as a convex relaxation of an intuitive but computationally hard integer programming problem. The objective function is highly symmetric, being invariant under unitary transformations of the text representations. Another key idea is to replace the constraint on the number of sentences in the summary with a convex surrogate. For solving the program we have designed a specific projected gradient descent algorithm and analyzed its performance in terms of execution time and quality of the approximation. Using the datasets DUC 2005 and Cornell Newsroom Summarization Dataset, we have shown empirically that the algorithm can provide competitive results for single document summarization and multi-document query-based summarization. On the Cornell Newsroom Summarization Dataset, it ranked second among the unsupervised methods tested. For the more challenging task of multi-document query-based summarization, the method was tested on the DUC 2005 Dataset. Our algorithm surpassed the other reported methods with respect to the ROUGE-SU4 metric, and it was at less than 0.01 from the top performing algorithms with respect to ROUGE-1 and ROUGE-2 metrics.

Generating meaningful summary for the given natural language text is one of the challenging and popular task in present era. Researchers have come up with various techniques for the abstractive and extractive summarization. This experimental study is focused on the extractive summarization. In graph-based extractive text summarization techniques, the sentences of the input document are used as the nodes of the graph and various similarity measurements are used to weight the edges of the graph. Each node’s rating is determined using the graph ranking algorithms, and the top-ranked nodes (sentences) are then added to the output extractive summary. In this work, we first translate the publicly available dataset into Hindi text using the Google Translate service. Next, we apply a pre-trained multi-lingual transformer to generate embedding vectors of each sentence of the document. We use these embedding vectors as the nodes of the graph. Rest of the approach remains unchanged. At last, we evaluate the generated extractive summaries on the basis on ROUGE score. Evaluation results indicate that the use of pre-trained multi-lingual transformer can be effective to generate more meaningful extractive summaries.

Graph Neural Networks (GNNs) are deep learning models specifically designed for analyzing graph-structured data, capturing complex relationships and structures to improve analysis and prediction. A common task in GNNs is node classification, where each node in the graph is assigned a predefined category. The Graph Attention Network (GAT) is a popular variant of GNNs known for its ability to capture complex dependencies by assigning importance weights to nodes during information aggregation. However, the GAT’s reliance on local attention mechanisms limits its effectiveness in capturing global information and long-range dependencies. To address this limitation, we propose a new attention mechanism called Global-Local Graph Attention (GLGA). Our mechanism enables the GAT to capture long-range dependencies and global graph structures while maintaining its ability to focus on local interactions. We evaluate our algorithm on three citation datasets (Cora, Citeseer, and Pubmed) using multiple metrics, demonstrating its superiority over other baseline models. The proposed GLGA mechanism has been proven to be an effective solution for improving node classification tasks.