Search

Abstract In the pharmaceutical industry, there is an abundance of regulatory documents used to understand the current regulatory landscape and proactively make project decisions. Due to the size of these documents, it is helpful for project teams to have informative summaries. We propose a novel solution, MedicoVerse, to summarize such documents using advanced machine learning techniques. MedicoVerse uses a multi-stage approach, combining word embeddings using the SapBERT model on regulatory documents. These embeddings are put through a critical hierarchical agglomerative clustering step, and the clusters are organized through a custom data structure. Each cluster is summarized using the bart-large-cnn-samsum model, and each summary is merged to create a comprehensive summary of the original document. We compare MedicoVerse results with established models T5, Google Pegasus, Facebook BART, and large language models such as Mixtral 8 $$\times $$ × 7b instruct, GPT 3.5, and Llama-2-70b by introducing a scoring system that considers four factors: ROUGE score, BERTScore, business entities and the Flesch Reading Ease. Our results show that MedicoVerse outperforms the compared models, thus producing informative summaries of large regulatory documents.

As the amount of the available information continues to grow, finding the relevant information has become increasingly challenging. As a solution, text summarization has emerged as a vital method for extracting essential information from lengthy documents. There are various techniques available for filtering documents and extracting the pertinent information. In this study, a comparative analysis is conducted to evaluate traditional approaches and state-of-the-art methods on the BBC News and CNN/DailyMail datasets. This study offers valuable insights for researchers to advance their research and helps practitioners in selecting the most suitable techniques for their specific use cases.

Abstract Background Text summarization is a challenging problem in Natural Language Processing, which involves condensing the content of textual documents without losing their overall meaning and information content, In the domain of bio-medical research, summaries are critical for efficient data analysis and information retrieval. While several bio-medical text summarizers exist in the literature, they often miss out on an essential text aspect: text semantics. Results This paper proposes a novel extractive summarizer that preserves text semantics by utilizing bio-semantic models. We evaluate our approach using ROUGE on a standard dataset and compare it with three state-of-the-art summarizers. Our results show that our approach outperforms existing summarizers. Conclusion The usage of semantics can improve summarizer performance and lead to better summaries. Our summarizer has the potential to aid in efficient data analysis and information retrieval in the field of biomedical research.

Natural language processing (NLP) performs a vital function in text summarization, a task targeted at refining the crucial information from the massive quantity of textual data. NLP methods allow computers to comprehend and process human language, permitting the development of advanced summarization methods. Text summarization includes the automatic generation of a concise and coherent summary of a specified document or collection of documents. Extracting significant insights from text data is crucial as it provides advanced solutions to end-users and business organizations. Automatic text summarization (ATS) computerizes text summarization by decreasing the initial size of the text without the loss of main data features. Deep learning (DL) approaches exhibited significant performance in abstractive and extractive summarization tasks. This research designed an extractive text summarization using NLP with an optimal DL (ETS-NLPODL) model. The major goal of the ETS-NLPODL technique was to exploit feature selection with a hyperparameter-tuned DL model for summarizing the text. In the ETS-NLPODL technique, an initial step of data preprocessing was involved to convert the input text into a compatible format. Next, a feature extraction process was carried out and the optimal set of features was chosen by the hunger games search optimization (HGSO) algorithm. For text summarization, the ETS-NLPODL model used an attention-based convolutional neural network with a gated recurrent unit (ACNN-GRU) model. Finally, the mountain gazelle optimization (MGO) algorithm was employed for the optimal hyperparameter selection of the ACNN-GRU model. The experimental results of the ETS-NLPODL system were examined under the benchmark dataset. The experimentation outcomes pointed out that the ETS-NLPODL technique gained better performance over other methods concerning diverse performance measures.

ABSTRACT Amharic is one of the under‐resourced languages, making news headline generation particularly challenging due to the scarcity of high‐quality linguistic datasets necessary for training effective natural language processing models. In this study, we fine‐tuned the small check point of the T5v1.1 model (t5‐small) to perform Amharic news headline generation with an Amharic dataset that is comprised of over 70k news articles along with their headline. Fine‐tuning the model involves dataset collection from Amharic news websites, text cleaning, news article size optimization using the TF‐IDF algorithm, and tokenization. In addition, a tokenizer model is developed using the byte pair encoding (BPE) algorithm prior to feeding the dataset for feature extraction and summarization. Metrics including Rouge‐L, BLEU, and Meteor were used to evaluate the performance of the model and a score of 0.5, 0.24, and 0.71, respectively, was achieved on the test partition of the dataset that contains 7230 instances. The results were good relative to result of the t5 model without fine‐tuning, which are 0.1, 0.03, and 0.14, respectively. A postprocessing technique using a rule‐based approach was used for further improving summaries generated by the model. The addition of the postprocessing helped the system to achieve Rouge‐L, BLEU, and Meteor scores of 0.72, 0.52, and 0.81, respectively. The result value is relatively better than the result achieved by the nonfine‐tuned T5v1.1 model and the result of previous studies report on abstractive‐based text summarization for Amharic language, which had a 0.27 Rouge‐L score. This contributes a valuable insight for practical application and further improvement of the model in the future by increasing the article length, using more training data, using machine learning–based adaptive postprocessing techniques, and fine‐tuning other available pretrained models for text summarization.

Text summarization is the task of generating a short and concise summary of a source text. In an abstractive text summarization, the generated summaries may potentially contain new phrases that do not appear in the source text. Dialogue summarization is a special case of text summarization in which the source text is a dialogue between two or more people. Dialogue summarization can be a crucial step especially when the source dialogues are complex and long such as call center conversations. Large language models (LLMs) show remarkable performance in natural language generation tasks and thus they can be a suitable modeling approach for abstractive text summarization. Although LLMs are extensively studied for common languages, there are only a few studies for underrepresented languages such as Turkish. In this paper, we make a comprehensive evaluation of LLMs for Turkish abstractive dialogue summarization. For this purpose, we translated 3 datasets in English to Turkish. Additionally, we make use of a test set that contains real call center dialogues originally collected in Turkish. In the experiments, we observe that fine-tuning LLMs to the dialogue summarization task significantly improves the performance. We obtain 21% overall absolute improvement with the fine-tuning over a baseline Turkish LLM. The performance is improved in all 4 test cases. Additionally, we observe that the length of the summaries plays a crucial role in the performance.

In this paper, we introduce an innovative approach that merges linguistic prompting with reinforcement learning to improve the quality of text summarization models. The primary focus is on enhancing the human-centered evaluation of these models, which is crucial for ensuring that the generated summaries are both useful and understandable. Our framework uses linguistic prompts as a guiding tool in the summarization process, providing more precise control over the resulting summaries. This method allows the summarization model to produce outputs that are not only accurate but also reflective of specific human-like cues, such as tone and context. By doing so, we can steer the model's behavior toward generating summaries that are more aligned with human expectations. To further refine the model's performance, we integrate reinforcement learning into our framework. This technique involves iterative improvement based on feedback from human evaluators, allowing the model to learn from its mistakes and continuously adapt to human preferences. This reinforcement-based approach ensures that the summarization model evolves over time, achieving greater accuracy and relevance with each iteration. Our methodology addresses a key challenge in text summarization: creating summaries that are concise yet sufficiently informative. By leveraging linguistic prompting and reinforcement learning, we aim to develop a system that produces summaries that are not only shorter but also more meaningful from a human perspective. This work contributes to the advancement of natural language processing by offering a novel way to balance brevity and informativeness, ultimately leading to more interpretable and human-friendly text summarization tasks.

Researchers consistently publish articles to contribute to science. However, it has become difficult to understand the terms employed in the document along with the way the semantic content is associated with other terms because of the rapid growth in the publication of scientific journals. Therefore, the generation of summaries based on scientific terms is more difficult with longer articles. The preparation of a summary with semantic relations between terms is addressed with graph-based techniques. However, graph-based methods are inadequately focused on generating summaries of scientific articles. To address this problem, a novel graph-based abstractive summarization (GBAS) model based on SciBERT and the graph transformer network (GTN) is proposed in this paper. The scientific content is encoded with SciBERT, terminology-related word extracts from the article with the Scientific Information Extractor (SciIE) system, and long documents are encoded and summarized with GTN. The proposed model is compared with baseline models. Experimental results show that the proposed model outperforms baseline methods in summarizing long scientific articles with ROUGE-L scores of 34.96.

The task of text summarization aims to provide highly condensed summaries of long textual information, with the ideal summary being both precise and concise. In recent years, there has been extensive research on the brevity of summaries, but these methods still have significant room for improvement in ROUGE scores, especially when the beam width is increased. We propose a new model called the DC (Dual-Level Contrastive Learning), which combines contrastive learning and data augmentation, and design a new scoring function during the training phase to enhance accuracy and conciseness. Ultimately, our framework achieves excellent ROUGE scores, ensuring concise and readable output even with increased beam width. Experimental results on the CNN/DailyMail (47.82 ROUGE-1, 0.017 VAR) and XSum (47.31 ROUGE-1, 0.0052 VAR) datasets demonstrate that our approach can significantly enhance the accuracy and conciseness of the summaries. Some metrics have exceeded those of the current state-of-the-art model BRIO, promoting the state-of-the-art performance to a higher level.

Urdu, being a common language in South Asia, has not received significant attention in terms of language processing compared to more advanced languages. In the field of Natural Language Processing (NLP), the task of text summarization holds great importance due to its ability to comprehend textual content and generate concise summaries. Text summarization can be either extractive or abstractive in nature. While considerable efforts have been made to advance extractive summarization techniques, the limitations associated with it have been extensively explored and explained in the paper. However, the domain of abstractive summarization for the Urdu language remains largely unexplored. The challenges and underlying factors that have impeded progress in this domain have also been addressed. This paper specifically focuses on abstractive summarization of the Urdu language using supervised learning. To accomplish this, a labeled dataset consisting of Urdu text and its abstractive summaries is required. A dataset of Urdu text and its corresponding abstractive summaries has been prepared for the purpose of supervised learning. Additionally, the paper presents the results of summary generation, measured in terms of a rough score. Transformer’s encoder-decoder network was employed to generate abstractive summaries in Urdu, yielding a ROUGE-1 score of 25.18 in Urdu text summarization. Moreover, a novel evaluation metric called the “disconnection rate” has been introduced as a context-aware evaluation metric to enhance the assessment of a summary, known as the Context Aware RoBERTa Score.

The paper describes automatic summarization as one of the topic that helps elearning system to be more adaptable on content generation. This article treat automatic summarization with approaches that provide the ability to summarize texts for different languages. In the case of this article, it is about the English, Romanian and Russian languages. The paper contains both the description of the problem and different approaches already used by other researchers. Next, the data with which the automatic summarization experiments were carried out were described. The metrics with which we can evaluate the quality of the summarization result were presented. Finally, some thoughts were formulated regarding the results obtained in the experiment.

Expert-caliber documents, reports, letters, and resumes can be easily developed using Microsoft Office. Microsoft Office offers capabilities such as grammar check, text and font checking & formatting, HTML compatibility, advanced page layout, image support, and more in contrast to a plain text editor, however, it does not have the autocomplete abbreviations feature. The paper proposes an Autocomplete abbreviation Recommendation System that will integrate the benefits of getting automatic suggestions of either full forms, abbreviations, or both by clicking on the option that is being suggested. This will provide more flexibility to the user using existing Microsoft Office platforms. To create this feature, we have examined the JavaScript JQuery functions to implement a basic autocomplete feature. Information overloading is also one of the most important problems brought on by the Internet's explosive expansion. Massive quantities of text are difficult for people to manually summarise. Thus, there is now a greater need for summarizers that are more sophisticated and potent. Hence, Python's packages, methods, and NLP are used in this work to implement Text Summarization. By using this technique, the phrase's overall meaning is enhanced and the reader's comprehension is enhanced.

Transfer learning approaches in natural language processing have been explored and evolved as a potential solution for solving many problems in recent days. The current research on aspect-based summarization shows unsatisfactory accuracy and low-quality generated summaries. Additionally, the potential advantages of combining language models with parallel processing have not been explored in the existing literature. This paper aims to address the problem of aspect-based extractive text summarization using a transfer learning approach and an optimization method based on map reduce. The proposed approach utilizes transfer learning with language models to extract significant aspects from the text. Subsequently, an optimization process using map reduce is employed. This optimization framework includes an in-node mapper and reducer algorithm to generate summaries for important aspects identified by the language model. This enhances the quality of the summary, leading to improved accuracy, particularly when applied to electrical power system documents. By leveraging the strengths of natural language models and parallel data processing techniques, this model presents an opportunity to achieve better text summary generation. The performance metric used is accuracy, measured with the ROUGE tool, incorporating precision, recall and f-measure. The proposed model demonstrates a 6% improvement in scores compared to state-of-the-art techniques.

Electronic health records (EHRs) are a critical tool in healthcare and capture a wide array of patient information that can inform clinical decision-making. However, the sheer volume and complexity of EHR data present challenges for healthcare providers, particularly in fast-paced environments such as intensive care units (ICUs). To address this problem, the automatic summarization of the main problems of patients from daily progress notes can be extremely helpful. Furthermore, by accurately predicting ICU patients’ lengths of stay (LOSs), resource allocation and management can be optimized, allowing for a more efficient flow of patients within the healthcare system. This work proposes a hybrid method to summarize EHR notes and studies the potential of these summaries together with structured data for the prediction of LOSs of ICU patients. Our investigation demonstrates the effectiveness of combining extractive and abstractive summarization techniques with a concept-based method combined with a text-to-text transfer transformer (T5), which shows the most promising results. By integrating the generated summaries and diagnoses with other features, our study contributes to the accurate prediction of LOSs, with a support vector machine emerging as our best-performing classifier with an accuracy of 77.5%, surpassing existing systems and highlighting the potential for optimal allocation of resources within ICUs.

This Various text summarization methods, such as extractive, abstractive, and human abstraction concepts have been compared in terms of performance, each with its specialties and limitations. This research analyses comparisons among the methods and some of their techniques used in text summarization. Our initial contribution is to suggest a thorough overview of the methods. The research methodology aims to compare text summarization methods through a systematic literature review to understand the topic and select appropriate methods. The search method involves keyword-based and citation-based techniques using academic search engines. The comparison of methods will consider various evaluation criteria such as document structure, content importance, quantitative approach, qualitative approach, dependency on machine learning, sentence generation, central concept identification, human involvement, representation in mathematics, and historical approaches. The methods would be evaluated based on these criteria to provide an objective and comprehensive comparison. No method consistently produces accurate text summaries. The best course of action will depend on the particulars and constraints of the current work because each method has both positive and negative aspects. The two primary methods for text summarization were discovered to be extractive and abstractive. This comparison study analysed various text summary and revealing each method's positive attributes and drawbacks. By giving a comprehensive overview of the main two methods, this comparative analysis advances the subject of text summarizing.

Making scribes and prescriptions are the primary activities for a health professional to serve the patients. Although in most of the cases these tasks are pursued manually, a few studies focused on developing digital scribe generation and prescription systems. Moreover, to enhance the effectiveness and adoption of such digital scribe and prescription systems, these systems should be intelligent and useable enough. Therefore, the objective of this research is to understand the user requirements for developing an automated scribes and intelligent prescribing system for health professionals and to develop the automated scribes and intelligent prescribing system based on the revealed users' requirements. And finally, to evaluate the performance of the proposed system. To attain these objectives, a requirement elicitation study was carried out following the semi-structured interviews to reveal the user requirements for an intelligent scribe and prescription system. The study proposed an automated digital scribe that can record medical information adopting the LSTM model; and also be able to generate automated prescriptions based on a doctor's voice command. Finally, the system was evaluated through an empirical study where participants (doctors) were asked to generate scribes and provide prescriptions manually and also by using the proposed system. The study found that the scribes and prescriptions generated using the proposed system are highly similar to the scribes (87.5 %) and prescriptions (96.2 %) generated manually. Analysis of the evaluation results also showed that the system provides a user-friendly, easy-to-use, intuitive, and interactive interface to facilitate the doctors and clinicians.

Extractive summarization, a pivotal task in natural language processing, aims to distill essential content from lengthy documents efficiently. Traditional methods often struggle with capturing the nuanced interdependencies between different document elements, which is crucial to producing coherent and contextually rich summaries. This paper introduces Multi-Element Contextual Hypergraph Extractive Summarizer (MCHES), a novel framework designed to address these challenges through an advanced hypergraph-based approach. MCHES constructs a contextual hypergraph where sentences form nodes interconnected by multiple types of hyperedges, including semantic, narrative, and discourse hyperedges. This structure captures complex relationships and maintains narrative flow, enhancing semantic coherence across the summary. The framework incorporates a Contextual Homogenization Module (CHM), which harmonizes features from diverse hyperedges, and a Hypergraph Contextual Attention Module (HCA), which employs a dual-level attention mechanism to focus on the most salient information. The innovative Extractive Read-out Strategy selects the optimal set of sentences to compose the final summary, ensuring that the latter reflects the core themes and logical structure of the original text. Our extensive evaluations demonstrate significant improvements over existing methods. Specifically, MCHES achieves an average ROUGE-1 score of 44.756, a ROUGE-2 score of 24.963, and a ROUGE-L score of 42.477 on the CNN/DailyMail dataset, surpassing the best-performing baseline by 3.662%, 3.395%, and 2.166% respectively. Furthermore, MCHES achieves BERTScore values of 59.995 on CNN/DailyMail, 88.424 on XSum, and 89.285 on PubMed, indicating superior semantic alignment with human-generated summaries. Additionally, MCHES achieves MoverScore values of 87.432 on CNN/DailyMail, 60.549 on XSum, and 59.739 on PubMed, highlighting its effectiveness in maintaining content movement and ordering. These results confirm that the MCHES framework sets a new standard for extractive summarization by leveraging contextual hypergraphs for better narrative and thematic fidelity.

This study presents a pioneering approach that leverages advanced sensing technologies and data processing techniques to enhance the process of clinical documentation generation during medical consultations. By employing sophisticated sensors to capture and interpret various cues such as speech patterns, intonations, or pauses, the system aims to accurately perceive and understand patient–doctor interactions in real time. This sensing capability allows for the automation of transcription and summarization tasks, facilitating the creation of concise and informative clinical documents. Through the integration of automatic speech recognition sensors, spoken dialogue is seamlessly converted into text, enabling efficient data capture. Additionally, deep models such as Transformer models are utilized to extract and analyze crucial information from the dialogue, ensuring that the generated summaries encapsulate the essence of the consultations accurately. Despite encountering challenges during development, experimentation with these sensing technologies has yielded promising results. The system achieved a maximum ROUGE-1 metric score of 0.57, demonstrating its effectiveness in summarizing complex medical discussions. This sensor-based approach aims to alleviate the administrative burden on healthcare professionals by automating documentation tasks and safeguarding important patient information. Ultimately, by enhancing the efficiency and reliability of clinical documentation, this innovative method contributes to improving overall healthcare outcomes.

Extractive text summarization selects asmall subset of sentences from a document, which gives good “coverage” of a document. When given a set of term weights indicating the importance of the terms, the concept of coverage may be formalized into a combinatorial optimization problem known as the budgeted maximum coverage problem. Extractive methods in this class are known to beamong the best of classic extractive summarization systems. This paper gives a synopsis of thesoftware package occams, which is a multilingual extractive single and multi-document summarization package based on an algorithm giving an optimal approximation to the budgeted maximum coverage problem. The occams package is written in Python and provides an easy-to-use modular interface, allowing it to work in conjunction with popular Python NLP packages, such as nltk, stanza or spacy.

The choice of this study has a significant impact on daily life. In various fields such as journalism, academia, business, and more, large amounts of text need to be processed quickly and efficiently. Text summarization is a technique used to generate a precise and shortened summary of spacious texts. The generated summary sustains overall meaning without losing any information and focuses on those parts that contain useful information. The goal is to develop a model that converts lengthy articles into concise versions. The task to be solved is to select an effective procedure to develop the model. Although the present text summarization models give us good results in many recognized datasets such as cnn/daily- mail, newsroom, etc. All the problems can not be resolved by these models. In this paper, a new text summarization method has been proposed: combining the Extractive and Abstractive Text Summarization technique. In the extractive-based method, the model generates a summary using Sentence Ranking Algorithm and passes this generated summary through an abstractive method. When using the sentence ranking algorithm, after rearranging the sentences, the relationship between one sentence and another sentence is destroyed. To overcome this situation, Pronoun to Noun conversion has been proposed with the new system. After generating the extractive summary, the generated summary is passed through the abstractive method. The proposed abstractive model consists of three pre-trained models: google/pegusus-xsum, face-book/bart-large-cnn model, and Yale-LILY/brio-cnndm-uncased, which generates a final summary depending on the maximum final score. The following results were obtained: experimental results on CNN/daily-mail dataset show that the proposed model obtained scores of ROUGE-1, ROUGE-2 and ROUGE-L are respectively 42.67 %, 19.35 %, and 39.57 %. Then, the result has been compared with three state-of-the-art methods: JEANS, DEATS and PGAN-ATSMT. The results outperform state-of-the-art models. Experimental results also show that the proposed model is qualitatively readable and can generate abstract summaries. Conclusion: In terms of ROUGE score, the model outperforms some art-of-the-state models for ROUGE-1 and ROUGE-L, but doesn’t achieve good result in ROUGE-2.

Extractive text summarization involves selecting and combining key sentences directly from the original text, rather than generating new content. While various methods, both statistical and graph-based, have been explored for this purpose, accurately capturing the intended meaning remains a challenge. To address this, researchers are investigating innovative techniques that harness deep learning models like BERT (Bidirectional Encoder Representations from Transformers). However, BERT has limitations in summarizing lengthy documents due to input length constraints. To find a more effective solution, we propose a novel approach. This approach combines the power of BERT, a transformer network pre-trained on extensive self-supervised datasets, with BiGRU (Bidirectional Gated Recurrent Units), a recurrent neural network that captures sequential dependencies within the text for extracting salient information. Our method involves using BERT to generate sentence-level embeddings, which are then fed into the BiGRU network. This allows us to achieve a comprehensive understanding of the complete document’s context. In experimental analysis conducted on arXiv and PubMed datasets, the proposed approach outperformed several state-of-the-art models. It achieved remarkable ROUGE-F scores of (46.7, 19.4, 35.4) and (47.0, 21.3, 39.7) on these datasets respectively. The proposed fusion of BERT and BiGRU significantly enhances extractive text summarization. It shows promising potential for summarizing lengthy documents and benefiting various domains that require concise and informative summaries.

Abstract Due to the exponential overflow of textual information in various fields of knowledge and on the internet, it is very challenging to extract important information or to generate a summary from some multi-document collection in a specific field. With such a gigantic amount of textual content, human text summarization becomes impractical since it is expensive and consumes a lot of time and effort. So, developing automatic text summarization (ATS) systems is becoming increasingly essential. ATS approaches are either extractive or abstractive. The extractive approach is simpler and faster than the abstractive approach. This work proposes an extractive ATS system that aims to extract a small subset of sentences from a large multi-document text. First, the whole text is preprocessed by applying some natural language processing techniques such as sentences segmentation, words tokenization, removal of stop-words, and stemming to provide a structured representation of the original document collection. Based on this structured representation, the ATS problem is formulated as a multi-objective optimization (MOO) problem that optimizes the extracted summary to maintain the coverage of the main text content while avoiding redundant information. Secondly, an evolutionary sparse multi-objective algorithm is developed to solve the formulated large-scale MOO. The output of this algorithm is a set of non-dominated summaries (Pareto front). A novel criterion is proposed to select the target summary from the Pareto front. The proposed ATS system has been examined using (DUC) datasets, and the output summaries have been evaluated using (ROUGE) metrics and compared with the literature.

Efficient Transformer models typically employ local and global attention methods, or utilize hierarchical or recurrent architectures, to process long text inputs in natural language processing tasks. However, these models face challenges in terms of sacrificing either efficiency, accuracy, or compatibility to develop their application in longer sequences. To maintain both the accuracy of global attention and the efficiency of local attention, while keeping a good compatibility to be easily applied to an existing pre-trained model, in this paper, we propose multi-level local attention (Mulla attention), which is a hierarchical local attention that acts on both the input sequence and multiple pooling sequences of different granularity simultaneously, thus performing long-range modeling while maintaining linear or log-linear complexity. We apply Mulla attention to LongT5 and implement our LongT5-Mulla sequence-to-sequence model, without introducing new parameters except for positional embeddings. Experiments show that our model can surpass all baseline models, including two original variants of LongT5, in the 8~16k-input long text summarization task on the Multi-News, arXiv and WCEP-10 datasets, with improvements of at least +0.22, +0.01, +0.52 percentage points (pp) averaged Rouge scores respectively, while at the meantime being able to effectively process longer sequences that have 16~48k tokens with at least 52.6% lower memory consumption than LongT5-tglobal, and +0.56~1.62 pp averaged Rouge scores higher than LongT5-local. These results demonstrate that our proposed LongT5-Mulla model can effectively process long sequences and extend the maximum input length for long text tasks from 16k to 48k while maintaining accuracy and efficiency.

In recent years,pretrained language models have developed rapidly,pushing natural language processing into a whole new stage of development.To help researchers understand where and how the powerful pretrained language models can be applied in natural language processing,this paper surveys the state-of-the-art of its application.Specifically,we first briefly review typical pretrained language models,including monolingual,multilingual and Chinese pretrained models.Then,we discuss these pretrained language models' contributions to five different natural language processing tasks:information extraction,sentiment analysis,question answering,text summarization,and machine translation.Finally,we discuss some challenges faced by the applications of pretrained language models.

Fine-tuning a pre-trained sequence-to-sequence-based language model has significantly advanced the field of abstractive summarization. However, the early models of abstractive summarization were limited by the gap between training and inference, and they did not fully utilize the potential of the language model. Recent studies have introduced a two-stage framework that allows the second-stage model to re-rank the candidate summary generated by the first-stage model, to resolve these limitations. In this study, we point out that the supervision method performed in the existing re-ranking model of the two-stage abstractive summarization framework cannot learn detailed and complex information of the data. In addition, we present the problem of positional bias in the existing encoder–decoder-based re-ranking model. To address these two limitations, this study proposes a hierarchical supervision method that jointly performs summary and sentence-level supervision. For sentence-level supervision, we designed two sentence-level loss functions: intra- and inter-intra-sentence ranking losses. Compared to the existing abstractive summarization model, the proposed method exhibited a performance improvement for both the CNN/DM and XSum datasets. The proposed model outperformed the baseline model under a few-shot setting.

Since the introduction of neural networks,text summarization techniques continue to attract the attention of resear-chers.Similarly,generative adversarial networks(GANs)can be used for text summarization because they can generate text features or learn the distribution of the entire sample and produce correlated sample points.In this paper,we exploit the features of generative adversarial networks(GANs)and use them for abstractive text summarization tasks.The proposed generative adversa-rial model has three components:a generator,which encodes the input sentences into shorter representations;a readability discriminator,which forces the generator to create comprehensible summaries;and a similarity discriminator,which acts on the generator to curb the discorrelation between the outputted text summarization and the inputted text summarization.In addition,Chinese WordNet is used as an external knowledge base in the similarity discriminator to enhance the discriminator.The generator is optimized using policy gradient algorithm,converting the problem into reinforcement learning.Experimental results show that the proposed model gets high ROUGE evaluation scores.

This paper use text summarization techniques as a tool for empirical legal research, creating a summary of the decisions given the phrases predictive power with regards to the decision outcome. A dataset of habeas corpus decisions from various courts in Brazil is used that explicitly cite the COVID pandemic as a reason for requesting the release of the patients. A predictive model is created and through this analysis we propose to find the arguments most correlated with the outcome.

With a rapid increase in the volume of textual data on the Internet, extracting useful information through innovative text mining techniques has become crucial. In this context, terminology jargon in the literature related to text-mining creates ambiguity and has made it very difficult for researchers to focus in a specific direction and bring innovation. For example, review mining and opinion mining may have different applications, however, from a technical perspective, they are very similar. In this paper, we propose a classification of the text mining terminologies from the perspectives of technical and text-mining processes. The classification is based on a comprehensive literature survey and analysis. This research study presents a clear classification of text mining terminologies based on technical and text mining processes to resolve the issue of terminology jargon. By utilizing the proposed classification, researchers will be able to easily choose a specific direction instead of diverging amongst similar research problems, thereby, driving innovation. Further, the proposed classification will help advance and improve the overall research progress in all text-mining related fields.

Background and Objectives: Text summarization plays an essential role in reducing time and cost in many domains such as medicine, engineering, etc. On the other hand, manual summarization requires much time. So, we need an automated system for summarizing. How to select sentences is critical in summarizing. Summarization techniques that have been introduced in recent years are usually greedy in the choice of sentences, which leads to a decrease in the quality of the summary. In this paper, a non-greedily method for selecting essential sentences from a text is presented.Methods: The present paper presents a method based on a generative adversarial network and attention mechanism called GAN-AM for extractive summarization. Generative adversarial networks have two generator and discriminator networks whose parameters are independent of each other. First, the features of the sentences are extracted by two traditional and embedded methods. We extract 12 traditional features. Some of these features are extracted from sentence words and others from the sentence. In addition, we use the well-known Skip-Gram model for embedding. Then, the features are entered into the generator as a condition, and the generator calculates the probability of each sentence in summary. A discriminator is used to check the generated summary of the generator and to strengthen its performance. We introduce a new loss function for discriminator training that includes generator output, real and fake summaries of each document. During training and testing, each document enters the generator with different noises. It allows the generator to see many combinations of sentences that are suitable for quality summaries.Results: We evaluate our results on CNN/Daily Mail and Medical datasets. Summaries produced by the generator show that our model performs better than other methods compared based on the ROUGE metric. We apply different sizes of noise to the generator to check the effect of noise on our model. The results indicate that the noise-free model has poor results.Conclusion: Unlike recent works, in our method, the generator selects sentences non-greedily. Experimental results show that the generator with noise can produce summaries that are related to the main subject.

Persuasive content in online news contains elements that aim to persuade its readers and may not necessarily include factual information. Since a news article only has some sentences that indicate persuasiveness, it would be quite challenging to differentiate news with or without the persuasive content. Recognizing persuasive sentences with a text summarization and classification approach is important to understand persuasive messages effectively. Text summarization identifies arguments and key points, while classification separates persuasive sentences based on the linguistic and semantic features used. Our proposed architecture includes text summarization approaches to shorten sentences without persuasive content and then using classifiers model to detect those with persuasive indication. In this paper, we compare the performance of latent semantic analysis (LSA) and TextRank in text summarization methods, the latter of which has outperformed in all trials, and also two classifiers of convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM). We have prepared a dataset (±1700 data and manually persuasiveness-labeled) consisting of news articles written in the Indonesian language collected from a nationwide electronic news portal. Comparative studies in our experimental results show that the TextRank–BERT–BiLSTM model achieved the highest accuracy of 95% in detecting persuasive news. The text summarization methods were able to generate detailed and precise summaries of the news articles and the deep learning models were able to effectively differentiate between persuasive news and real news.

The traditional Encoder-Decoder model with attention mechanism has such problems as text redundancy, inconsistent representation and out of vocabulary (OOV) in the application of the summary task, resulting in low accuracy of the generated summary. The transformer model with ambeddable text location information was improved, pointer network was introduced to help with decoding, and take advantage of pointer network to generated text to generate summary. The effectiveness of the transformer model was verified on the LCSTS Chinese short text summary data set. The results show that the model outperforms the benchmark model by an average of two points in ROUGE scores, and the prominence of the generated content and the fluency of the language are significantly improved while ensuring the consistency of the summary with the input text.

The scientific research process generally starts with the examination of the state of the art, which may involve a vast number of publications. Automatically summarizing scientific articles would help researchers in their investigation by speeding up the research process. The automatic summarization of scientific articles differs from the summarization of generic texts due to their specific structure and inclusion of citation sentences. Most of the valuable information in scientific articles is presented in tables, figures, and algorithm pseudocode. These elements, however, do not usually appear in a generic text. Therefore, several approaches that consider the particularity of a scientific article structure were proposed to enhance the quality of the generated summary, resulting in ad hoc automatic summarizers. This paper provides a comprehensive study of the state of the art in this field and discusses some future research directions. It particularly presents a review of approaches developed during the last decade, the corpora used, and their evaluation methods. It also discusses their limitations and points out some open problems. The conclusions of this study highlight the prevalence of extractive techniques for the automatic summarization of single monolingual articles using a combination of statistical, natural language processing, and machine learning techniques. The absence of benchmark corpora and gold standard summaries for scientific articles remains the main issue for this task.

Text summarization automatically produces a summary containing important sentences and includes all relevant important information from the original document. One of the main approaches, when viewed from the summary results, are extractive and abstractive. An extractive summary is heading towards maturity and now research has shifted towards abstractive summation and real-time summarization. Although there have been so many achievements in the acquisition of datasets, methods, and techniques published, there are not many papers that can provide a broad picture of the current state of research in this field. This paper provides a broad and systematic review of research in the field of text summarization published from 2008 to 2019. There are 85 journal and conference publications which are the results of the extraction of selected studies for identification and analysis to describe research topics/trends, datasets, preprocessing, features, techniques, methods, evaluations, and problems in this field of research. The results of the analysis provide an in-depth explanation of the topics/trends that are the focus of their research in the field of text summarization; provide references to public datasets, preprocessing and features that have been used; describes the techniques and methods that are often used by researchers as a comparison and means for developing methods. At the end of this paper, several recommendations for opportunities and challenges related to text summarization research are mentioned.

Objective: An area of research in which open science may have particularly high impact is in deep learning (DL), where researchers have developed many algorithms to solve challenging problems, but others may have difficulty in replicating results and applying these algorithms. In response, some researchers have begun to open up DL research by making their resources available (e.g., code, datasets and/or pre-trained models) to the research community. This article describes three case studies in DL where openly available resources are used and we investigate the impact on the projects, the outcomes, and make recommendations for what to focus on when making DL resources available.Methods: Each case study represents a single project using openly available DL resources for a research project. The process and progress of each case study is recorded along with aspects such as approaches taken, documentation of openly available resources, and researchers' experience with the openly available resources. The case studies are in multiple-document text summarization, optical character recognition (OCR) of thousands of text documents, and identifying unique language descriptors for sensory science.Results: Each case study was a success but had its own hurdles. Some takeaways are well-structured and clear documentation, code examples and demos, and pre-trained models were at the core to the success of these case studies.Conclusions: Openly available DL resources were the core of the success of our case studies. The authors encourage DL researchers to continue to make their data, code, and pre-trained models openly available where appropriate.

Automated information retrieval and text summarization concept is a difficult process in natural language processing because of the infrequent structure and high complexity of the documents. The text summarization process creates a summary by paraphrasing a long text. Earlier models on information retrieval and summarization are based on a massive labeled dataset by the use of handcrafted features, leveraging on knowledge for a particular domain, and concentrated on the narrow sub-domain to improve efficiency. This paper presents a new deep learning (DL) based information retrieval with a text summarization model. The proposed model involves three major processes namely information retrieval, template generation, and text summarization. Initially, the bidirectional long short term memory (BiLSTM) approach is employed for retrieving the textual data, which assumes each word in a sentence, extracts the information, and embeds it into the semantic vector. Next, the template generation process takes place using the DL model. The deep belief network (DBN) model is employed as a text summarization tool to summarize the textual content. In addition, the image description is generated for the visualized entities that exist in the images. The design of BiLSTM with the DBN model for the text summarization and image captioning process shows the novelty of the work. The performance of the presented method is validated using Giga word corpus and DUC corpus. The experimental results referred that the proposed DBN model outperformed the compared methods with the maximum precision, recall and F-score. The image captions are compared with a predefined set of captions that exists for the image and the performance is evaluated using the BLEU metric.

The explosion of online and offline data has changed how we gather, evaluate, and understand data. It is frequently difficult and time-consuming to comprehend large text documents and extract crucial information from them. Text summarization techniques address the mentioned problems by compressing long texts while retaining their essential contents. These techniques rely on the fast delivery of filtered, high-quality content to their users. Due to the massive amounts of data generated by technology and various sources, automated text summarization of large-scale data is challenging. There are three types of automatic text summarization techniques: extractive, abstractive, and hybrid. Regardless of these previous techniques, the generated summaries are a long way from the summarization produced by human experts. Although Arabic is a widely spoken language that is frequently used for content sharing on the web, Arabic text summarization of Arabic content is limited and still immature because of several problems, including the Arabic language’s morphological structure, the variety of dialects, and the lack of adequate data sources. This paper reviews text summarization approaches and recent deep learning models for this approach. Additionally, it focuses on existing datasets for these approaches, which are also reviewed, along with their characteristics and limitations. The most often used metrics for summarization quality evaluation are ROUGE1, ROUGE2, ROUGE L, and Bleu. The challenges that are encountered during Arabic text summarizing methods and approaches and the solutions proposed in each approach are analyzed. Many Arabic text summarization methods have problems, such as the lack of golden tokens during testing, being out of vocabulary (OOV) words, repeating summary sentences, lack of standard systematic methodologies and architectures, and the complexity of the Arabic language. Finally, providing the required corpora, improving evaluation using semantic representations, the lack of using rouge metrics in abstractive text summarization, and using recent deep learning models to adopt them in Arabic summarization studies is an essential demand.

The rapid expansion of social media platforms has resulted in an unprecedented surge of short text content being generated on a daily basis. Extracting valuable insights and patterns from this vast volume of textual data necessitates specialized techniques that can effectively condense information while preserving its core essence. In response to this challenge, automatic short text summarization (ASTS) techniques have emerged as a compelling solution, gaining significant importance in their development. This paper delves into the domain of summarizing short text on social media, exploring various types of short text and the associated challenges they present. It also investigates the approaches employed to generate concise and meaningful summaries. By providing a survey of the latest methods and potential avenues for future research, this paper contributes to the advancement of ASTS in the ever-evolving landscape of social media communication.

The extractive text summarization (ETS) method for finding the salient information from a text automatically uses the exact sentences from the source text. In this article, we answer the question of what quality of a summary we can achieve with ETS methods? To maximize the ROUGE-1 score, we used five approaches: (1) adapted reduced variable neighborhood search (RVNS), (2) Greedy algorithm, (3) VNS initialized by Greedy algorithm results, (4) genetic algorithm, and (5) genetic algorithm initialized by the Greedy algorithm results. Furthermore, we ran experiments on articles from the arXive dataset. As a result, we found 0.59 and 0.25 scores for ROUGE-1 and ROUGE-2, respectively achievable by the approach, where the genetic algorithm initialized by the Greedy algorithm results, which happens to yield the best results out of the tested approaches. Moreover, those scores appear to be higher than scores obtained by the current state-of-the-art text summarization models: the best score in the literature for ROUGE-1 on the same data set is 0.46. Therefore, we have room for the development of ETS methods, which are now undeservedly forgotten.

Text summarization is a subtask of natural language processing referring to the automatic creation of a concise and fluent summary that captures the main ideas and topics from one or multiple documents. Earlier literature surveys focus on extractive approaches, which rank the top-n most important sentences in the input document and then combine them to form a summary. As argued in the literature, the summaries of these approaches do not have the same lexical flow or coherence as summaries that are manually produced by humans. Newer surveys elaborate abstractive approaches, which generate a summary with potentially new phrases and sentences compared to the input document. Generally speaking, contrary to the extractive approaches, the abstractive ones create summaries that are more similar to those produced by humans. However, these approaches still lack the contextual representation needed to form fluent summaries. Recent advancements in deep learning and pretrained language models led to the improvement of many natural language processing tasks, including abstractive summarization. Overall, these surveys do not present a comprehensive evaluation framework that assesses the aforementioned approaches. Taking the above into account, the contribution of this survey is fourfold: (i) we provide a comprehensive survey of the state-of-the-art approaches in text summarization; (ii) we conduct a comparative evaluation of these approaches, using well-known datasets from the related literature, as well as popular evaluation scores such as ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-LSUM, BLEU-1, BLEU-2 and SACREBLEU; (iii) we report on insights gained on various aspects of the text summarization process, including existing approaches, datasets and evaluation methods, and we outline a set of open issues and future research directions; (iv) we upload the datasets and the code used in our experiments in a public repository, aiming to increase the reproducibility of this work and facilitate future research in the field.

The tremendous increase in documents available on the Web has turned finding the relevant pieces of information into a challenging, tedious, and time-consuming activity. Text summarization is an important natural language processing (NLP) task used to reduce the reading requirements of text. Automatic text summarization is an NLP task that consists of creating a shorter version of a text document which is coherent and maintains the most relevant information of the original text. In recent years, automatic text summarization has received significant attention, as it can be applied to a wide range of applications such as the extraction of highlights from scientific papers or the generation of summaries of news articles. In this research project, we are focused mainly on abstractive text summarization that extracts the most important contents from a text in a rephrased form. The main purpose of this project is to summarize texts in German. Unfortunately, most pretrained models are only available for English. We therefore focused on the German BERT multilingual model and the BART monolingual model for English, with a consideration of translation possibilities. As the source of the experiment setup, took the German Wikipedia article dataset and compared how well the multilingual model performed for German text summarization when compared to using machine-translated text summaries from monolingual English language models. We used the ROUGE-1 metric to analyze the quality of the text summarization.

The progress of communications over internet media such as social media and messengers has led to the production of large amount of textual data. This kind of information contains a lot of valuable knowledge and can be used to improve the performance of other NLP[1] tasks. There are several ways to use such information, one of which is text summarization Summarizing textual information can extract the main content of text within a short time. In this paper, we propose an approach for extractive summarization on Persian texts by using sentences embedding and a sparse coding framework. Most previous works focuses on text’s sentences individually which may not consider the hidden structure patterns between them. In this paper, our proposed approach can consider the relations between the text’s sentences by using three main criteria, namely coverage, diversity and sparsity, when selecting the summary sentences. By considering these criteria, we select sentences that can reconstruct the whole text with least reconstruction error. The proposed approach is evaluated on Persian dataset Pasokh and achieved 10.02% and 8.65% improvement compared to the state-of-the-art methods in rouge-1 and rouge-2 f-scores, respectively. We show that considering semantic relations among the text’s sentences can lead us to better sentence summarization. [1] Natural language processing

Internet or Web consists of a massive amount of information, handling which is a tedious task. Summarization plays a crucial role in extracting or abstracting key content from multiple sources with its meaning contained, thereby reducing the complexity in handling the information. Multi-document summarization gives the gist of the content collected from multiple documents. Temporal summarization concentrates on temporally related events. This paper proposes a Multi-Document Temporal Summarization (MDTS) technique that generates the summary based on temporally related events extracted from multiple documents. This technique extracts the events with the time stamp. TIMEML standards tags are used in extracting events and times. These event-times are stored in a structured database form for easier operations. Sentence ranking methods are build based on the frequency of events occurrences in the sentence. Sentence similarity measures are computed to eliminate the redundant sentences in an extracted summary. Depending on the required summary length, top-ranked sentences are selected to form the summary. Experiments are conducted on DUC 2006 and DUC 2007 data set that was released for multi-document summarization task. The extracted summaries are evaluated using ROUGE to determine precision, recall and F measure of generated summaries. The performance of the proposed method is compared with particle swarm optimization-based algorithm (PSOS), Cat swarm optimization-based summarization (CSOS), Cuckoo Search based multi-document summarization (MDSCSA). It is found that the performance of MDTS is better when compared with other methods. Doi: 10.28991/esj-2021-01268 Full Text: PDF

Text summarization is an information condensation technique that abbreviates a source document to a few representative sentences with the intention to create a coherent summary containing relevant information of source corpora. This promising subject has been rapidly developed since the advent of deep learning. However, summarization models based on deep neural network have several critical shortcomings. First, a large amount of labeled training data is necessary. This problem is standard for low-resource languages in which publicly available labeled data do not exist. In addition, a significant amount of computational ability is required to train neural models with enormous network parameters. In this study, we propose a model called Learning Free Integer Programming Summarizer (LFIP-SUM), which is an unsupervised extractive summarization model. The advantage of our approach is that parameter training is unnecessary because the model does not require any labeled training data. To achieve this, we formulate an integer programming problem based on pre-trained sentence embedding vectors. We also use principal component analysis to automatically determine the number of sentences to be extracted and to evaluate the importance of each sentence. Experimental results demonstrate that the proposed model exhibits generally acceptable performance compared with deep learning summarization models although it does not learn any parameters during the model construction process.

Precision education is a new challenge in leveraging artificial intelligence, machine learning, and learning analytics to enhance teaching quality and learning performance. To facilitate precision education, text marking skills can be used to determine students’ learning process. Text marking is an essential learning skill in reading. In this study, we proposed a model that leverages the state-of-the-art text summarization technique, Bidirectional Encoder Representations from Transformers (BERT), to calculate the marking score for 130 graduate students enrolled in an accounting course. Then, we applied learning analytics to analyze the correlation between their marking scores and learning performance. We measured students’ self-regulated learning (SRL) and clustered them into four groups based on their marking scores and marking frequencies to examine whether differences in reading skills and text marking influence students’ learning performance and awareness of self-regulation. Consistent with past research, our results did not indicate a strong relationship between marking scores and learning performance. However, high-skill readers who use more marking strategies perform better in learning performance, task strategies, and time management than high-skill readers who use fewer marking strategies. Furthermore, high-skill readers who actively employ marking strategies also achieve superior scores of environment structure, and task strategies in SRL than low-skill readers who are inactive in marking. The findings of this research provide evidence supporting the importance of monitoring and training students’ text marking skill and facilitating precision education.

Neural headline generation models have recently shown great results since neural network methods have been applied to text summarization. In this paper, we focus on news headline generation. We propose a news headline generation model based on a generative pre-training model. In our model, we propose a rich features input module. The headline generation model we propose only contains a decoder incorporating the pointer mechanism and the n-gram language features, while other generation models use the encoder-decoder architecture. Experiments on news datasets show that our model achieves comparable results in the field of news headline generation.

When people debate, they want to familiarize themselves with a whole range of arguments about a given topic in order to deepen their knowledge and inspire new claims. However, the amount of differently phrased arguments is humongous, making the process of processing them time-consuming. In spite of many works on using arguments (e.g. counter-argument generation), there is only a few studies on argument aggregation. To address this problem, we propose a new task in argument mining – Argument Extraction, which gathers similar arguments into key points, usually single sentences describing a set of arguments for a given debate topic. Such a short summary of related arguments has been manually created in previous research, while in our research key point generation becomes fully automatic, saving time and cost. As the first step of key point generation we explore existing similarity calculation methods, i.e. Sentence-BERT and MoverScore to investigate their performance. Next, we propose a combination of argument similarity and Maximal Marginal Relevance (MMR) for extracting key phrases to be utilized in our novel task of Argument Extraction. Experimental results show that MoverScore-based MMR outperforms strong baselines covering 72.5% of arguments when eleven or more arguments are extracted. This percentage is almost identical with the cover rate of human-made key points.

Text summarization is an important task in natural language processing (NLP). Neural summary models summarize information by understanding and rewriting documents through the encoder-decoder structure. Recent studies have sought to overcome the bias that cross-entropy-based learning methods can have through reinforcement learning (RL)-based learning methods or the problem of failing to learn optimized for metrics. However, the ROUGE metric with only $n$ -gram matching is not a perfect solution. The purpose of this study is to improve the quality of the summary statement by proposing a reward function used in text summarization based on RL. We propose ROUGE-SIM and ROUGE-WMD, modified functions of the ROUGE function. ROUGE-SIM enables meaningfully similar words, in contrast to ROUGE-L. ROUGE-WMD is a function adding semantic similarity to ROUGE-L. The semantic similarity between articles and summary text was computed using Word Mover’s Distance (WMD) methodology. Our model with two proposed reward functions demonstrated superior performance on ROUGE-1, ROUGE-2, and ROUGE_L than on ROUGE-L as a reward function. Our two models, ROUGE-SIM and ROUGE-WMD, scored 0.418 and 0.406 for ROUGE-L, respectively, for the Gigaword dataset. The two reward functions outperformed ROUGE-L even in the abstractiveness and grammatical aspects.

Legal judgments are generally very long, and relevant information is often scattered throughout the text. To complete a legal judgment summarization, capturing important, relevant information comprehensively from a lengthy text is crucial. The existing abstractive-summarization models based on pre-trained language have restrictions on the length of an input text. Another concern is that the generated summaries have not been well integrated with the legal judgment’s technical terms and specific topics. In this paper, we used raw legal judgments as information of different granularities and proposed a two-stage text-summarization model to handle different granularities of information. Specifically, we treated the legal judgments as a sequence of sentences and selected key sentence sets from the full texts as an input corpus for summary generation. In addition, we extracted keywords related to technical terms and specific topics in the legal texts and introduced them into the summary-generation model as an attention mechanism. The experimental results on the CAIL2020 and the LCRD datasets showed that our model achieved an overall 0.19–0.41 improvement in its ROUGE score, as compared to the baseline models. Further analysis also showed that our method could comprehensively capture essential and relevant information from lengthy legal texts and generate better legal judgment summaries.

In the last decade, the techniques of news aggregation and summarization have been increasingly gaining relevance for providing users on the web with condensed and unbiased information. Indeed, the recent development of successful machine learning algorithms, such as those based on the transformers architecture, have made it possible to create effective tools for capturing and elaborating news from the Internet. In this regard, this work proposes, for the first time in the literature to the best of the authors’ knowledge, a methodology for the application of such techniques in news related to cryptocurrencies and the blockchain, whose quick reading can be deemed as extremely useful to operators in the financial sector. Specifically, cutting-edge solutions in the field of natural language processing were employed to cluster news by topic and summarize the corresponding articles published by different newspapers. The results achieved on 22,282 news articles show the effectiveness of the proposed methodology in most of the cases, with 86.8% of the examined summaries being considered as coherent and 95.7% of the corresponding articles correctly aggregated. This methodology was implemented in a freely accessible web application.

Abstract Natural language processing has witnessed remarkable progress with the advent of deep learning techniques. Text summarization, along other tasks like text translation and sentiment analysis, used deep neural network models to enhance results. The new methods of text summarization are subject to a sequence-to-sequence framework of encoder–decoder model, which is composed of neural networks trained jointly on both input and output. Deep neural networks take advantage of big datasets to improve their results. These networks are supported by the attention mechanism, which can deal with long texts more efficiently by identifying focus points in the text. They are also supported by the copy mechanism that allows the model to copy words from the source to the summary directly. In this research, we are re-implementing the basic summarization model that applies the sequence-to-sequence framework on the Arabic language, which has not witnessed the employment of this model in the text summarization before. Initially, we build an Arabic data set of summarized article headlines. This data set consists of approximately 300 thousand entries, each consisting of an article introduction and the headline corresponding to this introduction. We then apply baseline summarization models to the previous data set and compare the results using the ROUGE scale.