Search

ion is a strategy that gives the essential points of a document in a short period of time. The video abstraction approach proposed in this research is based on multi-modal video data, which comprises both audio and visual data. Segmenting the input video into scenes and obtaining a textual and visual summary for each scene are the major video abstraction procedures to summarize the video events into a static document. To recognize the shot and scene boundary from a video sequence, a hybrid features method was employed, which improves detection shot performance by selecting strong and flexible features. The most informative keyframes from each scene are then incorporated into the visual summary. A hybrid deep learning model was used for abstractive text summarization. The BBC archive provided the testing videos, which comprised BBC Learning English and BBC News. In addition, a news summary dataset was used to train a deep model. The performance of the proposed approaches was assessed using metrics like Rouge for textual summary, which achieved a 40.49% accuracy rate. While precision, recall, and F-score used for visual summary have achieved (94.9%) accuracy, which performed better than the other methods, according to the findings of the experiments.

—In this paper we present the study on the potential of Natural Language Processing (NLP) to enhance the online bookstore customer experience. NLP is a subfield of computer science that studies computer-human language interaction. With the rise of virtual data, NLP has grown in importance, and it is now vital to develop NLP software capable of analyzing huge amounts of textual data. The proposed system integrates various NLP techniques. The ultimate goal is to offer an innovative and user-centric solution for online bookstores, showcasing the potential of NLP to revolutionize the virtual shopping experience. Additionally, a seminar on the latest advancements in NLP for the book industry is presented, covering the three key areas of text summarization, sentiment analysis of book reviews, and book search using image recognition and NLP. The seminar gives useful insight on the most recent advancements in NLP and offers an opportunity for stimulating discussion between academics, practitioners, and business leaders.

Along with the increasing number of scientific publications, many scientific communities must read the entire text to get the essence of information from a journal article. This will be quite inconvenient if the scientific journal article is quite long and there are more than one journals. Motivated by this problem, encourages the need for a method of text summarization that can automatically, concisely, and accurately summarize a scientific article document. The purpose of this research is to create an extractive text summarization by doing feature engineering to extract the semantic information from the original text. Comparing the long short-term memory algorithm and gated recurrent units and were used to get the most relevant sentences to be served as a summary. The results showed that both algorithms yielded relatively similar accuracy results, with gated recurrent units at 98.40% and long short-term memory at 98.68%. The evaluation method with matrix recall-oriented understudy for gisting evaluation (ROUGE) is used to evaluate the summary results. The summary results produced by the LSTM model compared to the summary results using the latent semantic analysis (LSA) method were then obtained recall values at ROUGE-1, ROUGE-2, and ROUGE-L respectively were 76.25%, 59.49%, and 72.72%.

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.

Text Summarization is a process which efficiently retrieves the relevant information from documents. The objective of the proposed, unsupervised approach is to summarize bug reports (software artefacts) with complete content and diversified information. The proposed approach utilizes Rapid Automatic Keyword Extraction and term frequency-inverse document frequency method to extract meaningful keywords and key-phrases with a relevant score. For sentence extraction, fuzzy C-means clustering is used to extracts sentences having high degree of membership from each cluster above a set threshold value. A rule-engine is used for sentence selection. The rules are generated with the domain knowledge and based on the extracted information by the keywords and sentences selected by the clustering method. Cohesive and coherent summary is generated by the proposed method on apache bug reports. For redundancy removal and to re-rank generated summary, hierarchical clustering is presented to enrich the extracted summary. The proposed approach is evaluated on newly constructed Apache project Bug Report Corpus (APBRC) and existing Bug Report Corpus (BRC). The results are compared on the basis of performance metrics such as precision, recall, pyramid precision and F-score. The experimental results depict that our proposed approach attains significant improvement over other baseline approaches such as BRC and LRCA. It also attains significant improvement over existing state-of-art unsupervised approaches such as Hurried, centroid and others. It extracts significant keyword phrases and sentences from each cluster to achieve full coverage and coherent summary. The results evaluated on APBRC corpus attains an average value of 78.22%, 82.18%, 80.10% and 81.66% for precision, recall, f-score and pyramid precision respectively.

Містить огляд літератури, присвяченої методам абстрактного реферування текстів. Розглянуто класифікацію методів абстрактного реферування. Із появою методів реферування текстів у 1950-х рр. техніки створення рефератів постійно покращувались, але оскільки абстрактне реферування потребує потужних технік для оброблення/генерації тексту, найбільший прогрес досягнуто в останні роки. Поточний швидкий розвиток у сфері як оброблення природної мови в цілому, так і автоматичного реферування зокрема робить особливо необхідним аналіз прогресу в цій сфері. Надано загальне уявлення як про попередні підходи, так і найновіші, включаючи пояснення методів і підходів. Додатково подано кількісні оцінки методів, запропонованих в оглянутих джерелах., The paper contains a literature review for automatic abstractive text summarization. The classification of abstractive text summarization methods was considered. Since the emergence of text summarization in the 1950s, techniques for summaries generation were constantly improving, but because the abstractive summarization require extensive language processing, the greatest progress was achieved only recently. Due to the current fast pace of development of both Natural Language Processing in general and Text Summarization in particular, it is essential to analyze the progress in these areas. The paper aims to give a general perspective on both the state-of-the-art and older approaches, while explaining the methods and approaches. Additionally, evaluation results of the research papers are presented., Содержит обзор литературы, посвященной методам абстрактного реферирования текстов. Рассмотрена классификация методов абстрактного реферирования. С появлением методов реферирования текстов в 1950-х гг. техники создания рефератов постоянно улучшались, но поскольку абстрактное реферирование требует мощных техник для обработки/генерации текста, наибольший прогресс был достигнут в последние годы. Текущее быстрое развитие в сфере как обработки естественного языка в целом, так и автоматического реферирования в частности делает особенно необходимым анализ прогресса в этой сфере. Дано общее представление как про более предыдущие подходы, так и про новые, включая обьяснение методов и подходов.Дополнительно представлены оценки методов, предложенных в рассмотреных работах.

Despite the availability of online educational resources about human papillomavirus (HPV), many women around the world may be prevented from obtaining the necessary knowledge about HPV. One way to mitigate the lack of HPV knowledge is the use of auto-generated text summarization tools. This study compares the level of HPV knowledge between women who read an auto-generated summary of HPV made using the BERT deep learning model and women who read a long-form text of HPV. We randomly assigned 386 women to two conditions: half read an auto-generated summary text about HPV (n = 193) and half read an original text about HPV (n = 193). We administrated measures of HPV knowledge that consisted of 29 questions. As a result, women who read the original text were more likely to correctly answer two questions on the general HPV knowledge subscale than women who read the summarized text. For the HPV testing knowledge subscale, there was a statistically significant difference in favor of women who read the original text for only one question. The final subscale, HPV vaccination knowledge questions, did not significantly differ across groups. Using BERT for text summarization has shown promising effectiveness in increasing women’s knowledge and awareness about HPV while saving their time.

The corpus contains 136,996 (argumentative text, conclusion) pairs. There are four variations of thiscorpus: base:(argumentative text, conclusion) pairs topic: (topic encoded argumentative text, conclusion) pairs targets:(topic and target encoded argumentative text, conclusion) pairs aspects:(topic and aspectencoded argumentative text, conclusion) pairs Each variation is split into train, val, and test files. Additionally, the test set used for automatic evaluation is provided (automatic_evaluation.csv) which must be used for any quantitative evaluation.&nbsp

Automatic text summarization attempts to provide an effective solution to today’s unprecedented growth of textual data. This paper proposes an innovative graph-based text summarization framework for generic single and multi document summarization. The summarizer benefits from two well-established text semantic representation techniques; Semantic Role Labelling (SRL) and Explicit Semantic Analysis (ESA) as well as the constantly evolving collective human knowledge in Wikipedia. The SRL is used to achieve sentence semantic parsing whose word tokens are represented as a vector of weighted Wikipedia concepts using ESA method. The essence of the developed framework is to construct a unique concept graph representation underpinned by semantic role-based multi-node (under sentence level) vertices for summarization. We have empirically evaluated the summarization system using the standard publicly available dataset from Document Understanding Conference 2002 (DUC 2002). Experimental results indicate that the proposed summarizer outperforms all state-of-the-art related comparators in the single document summarization based on the ROUGE-1 and ROUGE-2 measures, while also ranking second in the ROUGE-1 and ROUGE-SU4 scores for the multi-document summarization. On the other hand, the testing also demonstrates the scalability of the system, i.e., varying the evaluation data size is shown to have little impact on the summarizer performance, particularly for the single document summarization task. In a nutshell, the findings demonstrate the power of the role-based and vectorial semantic representation when combined with the crowd-sourced knowledge base in Wikipedia.

Teaching activities have nowadays been supported by a variety of electronic devices. Formative assessment tools allow teachers to evaluate the level of understanding of learners during frontal lessons and to tailor the next teaching activities accordingly. Despite plenty of teaching materials are available in the textual form, manually exploring these very large collections of documents can be extremely time-consuming. The analysis of learner-produced data (e.g., test outcomes) can be exploited to recommend short extracts of teaching documents based on the actual learner's needs. This paper proposes a new methodology to recommend summaries of potentially large teaching documents. Summary recommendations are customized to student's needs according to the results of comprehension tests performed at the end of frontal lectures. Specifically, students undergo multiple-choice tests through a mobile application. In parallel, a set of topic-specific summaries of the teaching documents is generated. They consist of the most significant sentences related to a specific topic. According to the results of the tests, summaries are personally recommended to students. We assessed the applicability of the proposed approach in real context, i.e., a B.S. university-level course. The results achieved in the experimental evaluation confirmed its usability.

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.

En los últimos años, las técnicas de deep learning han supuesto un gran impulso tecnológico en muchas de las tareas de Procesamiento de Lenguaje Natural (PLN). La tarea de generación de resúmenes también se ha beneficiado de estas técnicas, y en los últimos años se han implementado distintos modelos, logrando superar los resultados del estado de la cuestión. La mayoría de estos trabajos han sido evaluados en colecciones de textos periodísticos. Este artículo presenta un trabajo preliminar donde aplicamos un modelo transformador, BART, para la tarea de generación de resúmenes y lo evaluamos en varios datasets, uno de ellos formado por textos del dominio biomédico. = In recent years, deep learning techniques have provided a significant technological advance in many Natural Language Processing (NLP) tasks. Text summarization has also benefited from these techniques. Recently, several deep learning approaches have been implemented, surpassing the previous state of the art performances. Most of these works have been evaluated on collections of journalistic texts. This article presents a preliminary work where we apply a transforming model, BART, for text summarization. The model is evaluated on several datasets, one of them consisting of texts from the biomedical domain. Este trabajo ha sido nanciado por el Programa de Investigaci on del Ministerio de Economía y Competitividad del Gobierno de España, (Proyecto DeepEMR TIN2017-87548-C2-1-R) y por el Programa para proyectos interdisciplinares para jóvenes doctores en la Universidad Carlos III de Madrid financiado por la Comunidad de Madrid (Proyecto NLP4Rare-CM-UC3M).

En los últimos años, las técnicas de deep learning han supuesto un gran impulso tecnológico en muchas de las tareas de Procesamiento de Lenguaje Natural (PLN). La tarea de generación de resúmenes también se ha beneficiado de estas técnicas, y en los últimos años se han implementado distintos modelos, logrando superar los resultados del estado de la cuestión. La mayoría de estos trabajos han sido evaluados en colecciones de textos periodísticos. Este artículo presenta un trabajo preliminar donde aplicamos un modelo transformador, BART, para la tarea de generación de resúmenes y lo evaluamos en varios datasets, uno de ellos formado por textos del dominio biomédico. In recent years, deep learning techniques have provided a significant technological advance in many Natural Language Processing (NLP) tasks. Text summarization has also benefited from these techniques. Recently, several deep learning approaches have been implemented, surpassing the previous state of the art performances. Most of these works have been evaluated on collections of journalistic texts. This article presents a preliminary work where we apply a transforming model, BART, for text summarization. The model is evaluated on several datasets, one of them consisting of texts from the biomedical domain. Este trabajo ha sido financiado por el Programa de Investigación del Ministerio de Economía y Competitividad del Gobierno de España, (Proyecto DeepEMR TIN2017-87548-C2-1-R) y por el Programa para proyectos interdisciplinares para jóvenes doctores en la Universidad Carlos III de Madrid financiado por la Comunidad de Madrid (Proyecto NLP4Rare-CM-UC3M).

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.

Document summarization is the task of automatically generating a shorter version of a document or multiple documents while retaining the most important information. The task has received much attention in the natural language processing community due to its potential for various information access applications. Examples include tools that digest textual content (e.g., news, social media, reviews), answer questions, or provide recommendations. Summarization approaches are dedicated to processing single or multiple documents as well as creating extractive or abstractive summaries. In extractive summarization, summaries are formed by copying and concatenating the most important spans (usually sentences) from the input text, while abstractive approaches are able to generate summaries using words or phrases that are not in the original text. A core module within summarization is how to represent documents and distill information for downstream tasks (e.g., abstraction or extraction). Thanks to the popularity of neural network models and their ability to learn continuous representations, many new systems have been proposed for document modeling and summarization in recent years. This thesis investigates different approaches with neural network models to address the document summarization problem. We develop several novel neural models considering extractive and abstractive approaches for both single-document and multi-document scenarios. We first investigate how to represent a single document with a randomly initialized neural network. Contrary to previous approaches that ignore document structure when encoding the input, we propose a structured attention mechanism, which can impose a structural bias of document-level dependency trees when modeling a document, generating more powerful document representations. We first apply this model to the task of document classification, and subsequently to extractive single-document summarization using an iterative refinement process to learn more complex tree structures. Experimental results on both tasks show that the structured attention mechanism achieves competitive performance. Very recently, pretrained language models have achieved great success on several natural language understanding tasks by training large neural models on an enormous corpus with a language modeling objective. These models learn rich contextual information and to some extent are able to learn the structure of the input text. While summarization systems could in theory also benefit from pretrained language models, there are some potential obstacles to applying these pretrained models to document summarization tasks. The second part of this thesis focuses on how to represent a single document with pretrained language models. Beyond previous approaches that learn solely from the summarization dataset, this thesis proposes a framework for using pretrained language models as encoders for both extractive and abstractive summarization. The framework achieves state-of-the-art results on three datasets. Finally, in the third part of this thesis, we move beyond single documents and explore approaches for using neural networks for summarizing multiple documents. We analyze why the application of existing neural summarization models to this task is challenging and develop a novel modeling framework. More concretely, we propose a ranking-based pipeline and a hierarchical neural encoder for processing multiple input documents. Experiments on a large-scale multi-document summarization dataset, show that our system can achieve promising performance.

Neural networks based on the attentional encoder-decoder model have good capability in abstractive text summarization. However, these models are hard to be controlled in the process of generation, which leads to a lack of key information. And some key information, such as time, place, and people, is indispensable for humans to understand the main content. In this paper, we propose a key information guide network for abstractive text summarization based on a multi-task learning framework. The core idea is to automatically extract the key information that people need most in an end-to-end way and use it to guide the generation process, so as to get a more human-compliant summary. In our model, the document is encoded into two parts: results of the normal document encoder and the key information encoding, and the key information includes the key sentences and the keywords. A multi-task learning framework is introduced to get a more sophisticated end-to-end model. To fuse the key information, we propose a novel multi-view attention guide network to obtain the dynamic representations of the source text and the key information. In addition, the dynamic representations are incorporated into the abstractive module to guide the process of summary generation. We evaluate our model on the CNN/Daily Mail dataset and experimental results show that our model leads to significant improvements.

Event-related collections, including both tweets and webpages, have valuable information, and are worth exploring in interdisciplinary research and education. Unfortunately, such data is noisy, so this variety of information has not been adequately exploited. Further, for better understanding, more knowledge hidden behind events needs to be unearthed. Regarding these collections, different societies may have different requirements in particular scenarios. Some may need relatively clean datasets for data exploration and data mining. Social researchers require preprocessing of information, so they can conduct analyses. General societies are interested in the overall descriptions of events. However, few systems, tools, or methods exist to support the flexible use of event-related collections. In this research, we propose a new, integrated system to process and analyze event-related collections at different levels (i.e., data, information, and knowledge). It also provides various services and covers the most important stages in a system pipeline, including collection development, curation, analysis, integration, and visualization. Firstly, we propose a query likelihood model with pre-query design and post-query expansion to rank a webpage corpus by query generation probability, and retrieve relevant webpages from event-related tweet collections. We further preserve webpage data into WARC files and enrich original tweets with webpages in JSON format. As an application of data management, we conduct an empirical study of the embedded URLs in tweets based on collection development and data curation techniques. Secondly, we develop TwiRole, an integrated model for 3-way user classification on Twitter, which detects brand-related, female-related, and male-related tweeters through multiple features with both machine learning (i.e., random forest classifier) and deep learning (i.e., an 18-layer ResNet) techniques. As guidance to user-centered social research at the information level, we combine TwiRole with a pre-trained recurrent neural network-based emotion detection model, and carry out tweeting pattern analyses on disaster-related collections. Finally, we propose a tweet-guided multi-document summarization (TMDS) model, which generates summaries of the event-related collections by using tweets associated with those events. The TMDS model also considers three aspects of named entities (i.e., importance, relatedness, and diversity) as well as topics, to score sentences in webpages, and then rank selected relevant sentences in proper order for summarization. The entire system is realized using many technologies, such as collection development, natural language processing, machine learning, and deep learning. For each part, comprehensive evaluations are carried out, that confirm the effectiveness and accuracy of our proposed approaches. Regarding broader impact, the outcomes proposed in our study can be easily adopted or extended for further event analyses and service development. Doctor of Philosophy Event-related collections, including both tweets and webpages, have valuable information. They are worth exploring in interdisciplinary research and education. Unfortunately, such data is noisy. Many tweets and webpages are not relevant to the events. This leads to difficulties during data analysis of the datasets, as well as explanation of the results. Further, for better understanding, more knowledge hidden behind events needs to be unearthed. Regarding these collections, different groups of people may have different requirements. Some may need relatively clean datasets for data exploration. Some require preprocessing of information, so they can conduct analyses, e.g., based on tweeter type or content topic. General societies are interested in the overall descriptions of events. However, few systems, tools, or methods exist to support the flexible use of event-related collections. Accordingly, we describe our new framework and integrated system to process and analyze event-related collections. It provides varied services and covers the most important stages in a system pipeline. It has sub-systems to clean, manage, analyze, integrate, and visualize event-related collections. It takes an event-related tweet collection as input and generates an event-related webpage corpus by leveraging Wikipedia and the URLs embedded in tweets. It also combines and enriches original tweets with webpages. As an application of data management, we conduct an empirical study of tweets and their embedded URLs. We developed TwiRole for 3-way user classification on Twitter. It detects brand-related, female-related, and male-related tweeters through their profiles, tweets, and images. To aid user-centered social research, we combine TwiRole with an existing emotion detection tool, and carry out tweeting pattern analyses on disaster-related collections. Finally, we propose a tweet-guided multi-document summarization (TMDS) model and service, which generates summaries of the event-related collections by using tweets associated with those events. It extracts important sentences across different topics from webpages, and organizes them in proper order. The entire system is realized using many technologies, such as collection development, natural language processing, machine learning, and deep learning. For each part, comprehensive evaluations help confirm the effectiveness and accuracy of our proposed approaches. Regarding broader impact, our methods and system can be easily adopted or extended for further event analyses and service development.

© 2020 - IOS Press and the authors. All rights reserved. Currently, each person produces 1.7MB of information every second in different formats. However, the vast majority of information is text. This has increased the interest to study techniques to automate the identification of the relevant portions of text documents in order to offer as a result an automatic summary. This article presents a technique to extract the most representative sentences of a document taking into account by the user's criteria. These criteria are learned using a neural network, from a minimum set of documents whose sentences have been rated by the user in terms of importance. To verify the performance of the proposed methodology, we used 220 scientific articles from the PLOS Medicine journal published between 2004 and 2016. The results obtained have been very satisfactory.

© 2020 - IOS Press and the authors. All rights reserved. Currently, each person produces 1.7MB of information every second in different formats. However, the vast majority of information is text. This has increased the interest to study techniques to automate the identification of the relevant portions of text documents in order to offer as a result an automatic summary. This article presents a technique to extract the most representative sentences of a document taking into account by the user's criteria. These criteria are learned using a neural network, from a minimum set of documents whose sentences have been rated by the user in terms of importance. To verify the performance of the proposed methodology, we used 220 scientific articles from the PLOS Medicine journal published between 2004 and 2016. The results obtained have been very satisfactory.

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.

There is enormous amount information available in different forms of sources and genres. In order to extract useful information from a massive amount of data, automatic mechanism is required. The text summarization systems assist with content reduction keeping the important information and filtering the non-important parts of the text. Good document representation is really important in text summarization to get relevant information. Bag-of-words cannot give word similarity on syntactic and semantic relationship. Word embedding can give good document representation to capture and encode the semantic relation between words. Therefore, centroid based on word embedding representation is employed in this paper. Myanmar news summarization based on different word embedding is proposed. In this paper, Myanmar local and international news are summarized using centroid-based word embedding summarizer using the effectiveness of word representation approach, word embedding. Experiments were done on Myanmar local and international news dataset using different word embedding models and the results are compared with performance of bag-of-words summarization. Centroid summarization using word embedding performs comprehensively better than centroid summarization using bag-of-words.

Evaluation is crucial in the research and development of automatic summarization applications, in order to determine the appropriateness of a summary based on different criteria, such as the content it contains, and the way it is presented. To perform an adequate evaluation is of great relevance to ensure that automatic summaries can be useful for the context and/or application they are generated for. To this end, researchers must be aware of the evaluation metrics, approaches, and datasets that are available, in order to decide which of them would be the most suitable to use, or to be able to propose new ones, overcoming the possible limitations that existing methods may present. In this article, a critical and historical analysis of evaluation metrics, methods, and datasets for automatic summarization systems is presented, where the strengths and weaknesses of evaluation efforts are discussed and the major challenges to solve are identified. Therefore, a clear up-to-date overview of the evolution and progress of summarization evaluation is provided, giving the reader useful insights into the past, present and latest trends in the automatic evaluation of summaries. This research is partially funded by the European Commission under the Seventh (FP7 - 2007- 2013) Framework Programme for Research and Technological Development through the SAM (FP7-611312) project; by the Spanish Government through the projects VoxPopuli (TIN2013-47090-C3-1-P) and Vemodalen (TIN2015-71785-R), the Generalitat Valenciana through project DIIM2.0 (PROMETEOII/2014/001), and the Universidad Nacional de Educación a Distancia through the project “Modelado y síntesis automática de opiniones de usuario en redes sociales” (2014-001-UNED-PROY).

Today's news agencies are moving from traditional journalism, where publishing just a few news articles per day was sufficient, to modern content generation mechanisms, which create more than thousands of news pieces every day. With the growth of these modern news agencies comes the arduous task of properly handling this massive amount of data that is generated for each news article. Therefore, news agencies are constantly seeking solutions to facilitate and automate some of the tasks that have been previously done by humans. In this dissertation, we focus on some of these problems and provide solutions for two broad problems which help a news agency to not only have a wider view of the behaviour of readers around the article but also to provide an automated tools to ease the job of editors in summarizing news articles. These two disjoint problems are aiming at improving the users' reading experience by helping the content generator to monitor and focus on poorly performing content while allow them to promote the good-performing ones. We first focus on the task of popularity prediction of news articles via a combination of regression, classification, and clustering models. We next focus on the problem of generating automated text summaries for a long news article using deep learning models. The first problem aims at helping the content developer in understanding of how a news article is performing over the long run while the second problem provides automated tools for the content developers to generate summaries for each news article. Doctor of Philosophy Nowadays, each person is exposed to an immense amount of information from social media, blog posts, and online news portals. Among these sources, news agencies are one of the main content providers for each person around the world. Contemporary news agencies are moving from traditional journalism to modern techniques from different angles. This is achieved either by building smart tools to track the behaviour of readers’ reaction around a specific news article or providing automated tools to facilitate the editor’s job in providing higher quality content to readers. These systems should not only be able to scale well with the growth of readers but also they have to be able to process ad-hoc requests, precisely since most of the policies and decisions in these agencies are taken around the result of these analytical tools. As part of this new movement towards adapting new technologies for smart journalism, we have worked on various problems with The Washington Post news agency on building tools for predicting the popularity of a news article and automated text summarization model. We develop a model that monitors each news article after its publication and provide prediction over the number of views that this article will receive within the next 24 hours. This model will help the content creator to not only promote potential viral article in the main page of the web portal or social media, but also provide intuition for editors on potential poorly performing articles so that they can edit the content of those articles for better exposure. On the other hand, current news agencies are generating more than a thousands news articles per day and generating three to four summary sentences for each of these news pieces not only become infeasible in the near future but also very expensive and time-consuming. Therefore, we also develop a separate model for automated text summarization which generates summary sentences for a news article. Our model will generate summaries by selecting the most salient sentence in the news article and paraphrase them to shorter sentences that could represent as a summary sentence for the entire document.

Over the last few years, email has met with enormous popularity. People send and receive a lot of messages every day, connect with colleagues and friends, share files and information. Unfortunately, the email overload outbreak has developed into a personal trouble for users as well as a financial concerns for businesses. Accessing an ever-increasing number of lengthy emails in the present generation has become a major concern for many users. Email text summarization is a promising approach to resolve this challenge. Email messages are general domain text, unstructured and not always well developed syntactically. Such elements introduce challenges for study in text processing, especially for the task of summarization. This research employs a quantitative and inductive methodologies to implement the Unsupervised learning models that addresses summarization task problem, to efficiently generate more precise summaries and to determine which approach of implementing Unsupervised clustering models outperform the best. The precision score from ROUGE-N metrics is used as the evaluation metrics in this research. This research evaluates the performance in terms of the precision score of four different approaches of text summarization by using various combinations of feature embedding technique like Word2Vec /BERT model and hybrid/conventional clustering algorithms. The results reveals that both the approaches of using Word2Vec and BERT feature embedding along with hybrid PHA-ClusteringGain k-Means algorithm achieved increase in the precision when compared with the conventional k-means clustering model. Among those hybrid approaches performed, the one using Word2Vec as feature embedding method attained 55.73% as maximum precision value.

The advent of the sequence-to-sequence model and the attention mechanism has increased the comprehension and readability of automatically generated summaries. However, most previous studies on text summarization have focused on generating or extracting sentences only from an original text, even though every text has a latent topic category. That is, even if a topic category helps improve the summarization quality, there have been no efforts to utilize such information in text summarization. Therefore, this paper proposes a novel topical category-aware neural text summarizer which is differentiated from legacy neural summarizers in that it reflects the topic category of an original text into generating a summary. The proposed summarizer adopts the class activation map (CAM) as topical influence of the words in the original text. Since the CAM excerpts the words relevant to a specific category from the text, it allows the attention mechanism to be influenced by the topic category. As a result, the proposed neural summarizer reflects the topical information of a text as well as the content information into a summary by combining the attention mechanism and CAM. The experiments on The New York Times Annotated Corpus show that the proposed model outperforms the legacy attention-based sequence-to-sequence model, which proves that it is effective at reflecting a topic category into automatic summarization.

Natural language processing is the trending topic in the latest research areas, which allows the developers to create the human-computer interactions to come into existence. The natural language processing is an integration of artificial intelligence, computer science and computer linguistics. The research towards natural Language Processing is focused on creating innovations towards creating the devices or machines which operates basing on the single command of a human. It allows various Bot creations to innovate the instructions from the mobile devices to control the physical devices by allowing the speech-tagging. In our paper, we design a search engine which not only displays the data according to user query but also performs the detailed display of the content or topic user is interested for using the summarization concept. We find the designed search engine is having optimal response time for the user queries by analyzing with number of transactions as inputs. Also, the result findings in the performance analysis show that the text summarization method has been an efficient way for improving the response time in the search engine optimizations.

This paper presents tackling of a hard optimization problem of computational linguistics, specifically automatic multi-document text summarization, using grid computing. The main challenge of multi-document summarization is to extract the most relevant and unique information effectively and efficiently from a set of topic-related documents, constrained to a specified length. In the Big Data/Text era, where the information increases exponentially, optimization becomes essential in selection of the most representative sentences for generating the best summaries. Therefore, a data-driven summarization model is proposed and optimized during a run of Differential Evolution (DE). Different DE runs are distributed to a grid in parallel as optimization tasks, seeking high processing throughput despite the demanding complexity of the linguistic model, especially on longer multi-documents where DE improves results given more iterations. Namely, parallelization and the grid enable, running several independent DE runs at same time within fixed real-time budget. Such approach results in improving a Document Understanding Conference (DUC) benchmark recall metric over a previous setting. This paper is based upon work from COST Action IC1406High-Performance Modelling and Simulation for Big Data Appli-cations (cHiPSet), supported by COST (European Cooperation inScience and Technology). This paper is also based upon workfrom COST Actions CA15140 “Improving Applicability of Nature-Inspired Optimisation by Joining Theory and Practice (ImAppNIO)”, and CA18231 “Multi3Generation: Multi-task, Multilingual, Multi-modal Language Generation”, both supported by COST. The author AZ acknowledges the financial support from the Slovenian Research Agency (Research Core Funding No. P2-0041). AZ also acknowledges EU support under Project No. 5442-24/2017/6 (HPC – RIVR). AZ also acknowledges the EU Interreg Alpine Space project SmartVillages and Erasmus TSM grant. The author EL acknowledges the financial support by the Generalitat Valenciana through the Research Project PROMETEU/2018/089, and by the Spanish Government through the INTEGER project (RTI2018-094649-B-I00), and network RED iGLN (TIN2017-90773-REDT).

In an age overflowing with information, the task of converting unstructured data into structured data are a vital task of great need. Currently, most relation extraction modules are more focused on the extraction of local mention-level relations&mdash, usually from short volumes of text. However, in most cases, the most vital and important relations are those that are described in length and detail. In this research, we propose GREG: A Global level Relation Extractor model using knowledge graph embeddings for document-level inputs. The model uses vector representations of mention-level &lsquo, local&rsquo, relation&rsquo, s to construct knowledge graphs that can represent the input document. The knowledge graph is then used to predict global level relations from documents or large bodies of text. The proposed model is largely divided into two modules which are synchronized during their training. Thus, each of the model&rsquo, s modules is designed to deal with local relations and global relations separately. This allows the model to avoid the problem of struggling against loss of information due to too much information crunched into smaller sized representations when attempting global level relation extraction. Through evaluation, we have shown that the proposed model yields high performances in both predicting global level relations and local level relations consistently.

For software maintenance, bug reports provide useful information to developers because they can be used for various tasks such as debugging and understanding previous changes. However, as they are typically written in the form of conversations among developers, bug reports tend to be unnecessarily long and verbose, with the consequence that developers often have difficulties reading or understanding bug reports. To mitigate this problem, methods that automatically generate a summary of bug reports have been proposed, and various related studies have been conducted. However, existing bug report summarization methods have not fully exploited the inherent characteristics of bug reports. In this paper, we propose a bug report summarization method that uses the weighted-PageRank algorithm and exploits the 'duplicates&rsquo, &lsquo, blocks&rsquo, and &lsquo, depends-on&rsquo, relationships between bug reports. The experimental results show that our method outperforms the state-of-the-art method in terms of both the quality of the summary and the number of applicable bug reports.

The research aimed at providing an outcome summary of extraordinary events information for public health surveillance systems based on the extraction of online medical articles. The data set used is 7,346 pieces. Characteristics possessed by online medical articles include paragraphs that comprise more than one and the core location of the story or important sentences scattered at the beginning, middle and end of a paragraph. Therefore, this study conducted a summary by maintaining important phrases related to the information of extraordinary events scattered in every paragraph in the medical article online. The summary method used is maximal marginal relevance with an n-best value of 0.7. While the multi feature selection in question is the use of features to improve the performance of the summary system. The first feature selection is the use of title and statistic number of word and noun occurrence, and weighting tf-idf. In addition, other features are word level category in medical content patterns to identify important sentences of each paragraph in the online medical article. The important sentences defined in this study are classified into three categories: core sentence, explanatory sentence, and supporting sentence. The system test in this study was divided into two categories, such as extrinsic and intrinsic test. Extrinsic test is comparing the summary results of the decisions made by the experts with the output resulting from the system. While intrinsic test compared three n-Best weighting value method, feature selection combination, and combined feature selection combination with word level category in medical content. The extrinsic evaluation result was 72%. While intrinsic evaluation result of feature selection combination merger method with word category in medical content was 91,6% for precision, 92,6% for recall and f-measure was 92,2%.

Speech, is the most powerful way of communication with which human beings express their thoughts and feelings through different languages. The features of speech differs with each language. However, even while communicating in the same language, the pace and the dialect varies with each person. This creates difficulty in understanding the conveyed message for some people. Sometimes lengthy speeches are also quite difficult to follow due to reasons such as different pronunciation, pace and so on. Speech recognition which is an inter disciplinary field of computational linguistics aids in developing technologies that empowers the recognition and translation of speech into text. Text summarization extracts the utmost important information from a source which is a text and provides the adequate summary of the same. The research work presented in this paper describes an easy and effective method for speech recognition. The speech is converted to the corresponding text and produces summarized text. This has various applications like lecture notes creation, summarizing catalogues for lengthy documents and so on. Extensive experimentation is performed to validate the efficiency of the proposed method

Text summarization is the task of condensing a document keeping the relevant information. This task integrated in wider information systems can help users to access key information without having to read everything, allowing for a higher efficiency. In this research work, we have developed and evaluated a single-document extractive summarization approach, named SemPCA-Summarizer, which reduces the dimension of a document using Principal Component Analysis technique enriched with semantic information. A concept-sentence matrix is built from the textual input document, and then, PCA is used to identify and rank the relevant concepts, which are used for selecting the most important sentences through different heuristics, thus leading to various types of summaries. The results obtained show that the generated summaries are very competitive, both from a quantitative and a qualitative viewpoint, thus indicating that our proposed approach is appropriate for briefly providing key information, and thus helping to cope with a huge amount of information available in a quicker and efficient manner. This research work has been partially funded by the Generalitat Valenciana and the Spanish Government through the projects PROMETEOII/2014/001, TIN2015-65100-R, and TIN2015-65136-C2-2-R.

Learning something new from a text requires the reader to build on existing knowledge and add new material at the same time. Therefore, we propose collection-document (CDS) summaries that highlight commonalities and differences between a collection (or a single document) and a single document. We devise evaluation metrics that do not require human judgement, and three algorithms for extracting CDS that are based on single-document keyword-extraction methods. Our evaluation shows that different algorithms have different strengths, e.g. TF-IDF based approach best describes document overlap while the adaption of Rake provides keywords with a broad topical coverage. The proposed criteria and procedure can be used to evaluate document-collection summaries without annotated corpora or provide additional insight in an evaluation with human-generated ground truth.

Today, the tremendous information is available on the internet; it is difficult to get the information fast and most efficiently. There are so many text materials available on the internet, in order to extract the most relevant information from it, we need a good mechanism. Text summarization technique deals with the compression of large document into shorter version of text. Text summarizations choose the most significant part of text and create coherent summaries that state the main purpose of the given document. Extraction based text summarization involves selecting sentences of high relevance (rank) from the document based on word and sentence features and put them together to generate summary. This is modeled using Fuzzy Inference System. The summary of the document is created based upon the level of the importance of the sentences in the document. This paper focuses on the Fuzzy logic Extraction approach for text summarization and the semantic approach of text summarization using Latent Semantic Analysis.

Text Classification is an important technique for handling the huge and increasing amount of text documents on the web. An important problem of text classification is features selection. Many feature selection techniques were used in order to solve this problem, such as chi-square (CHI). Rather than using these techniques, this paper proposes a method for feature selection based on text summarization. We demonstrate this method on Arabic text documents and use text summarization for feature selection. Support Vector Machine (SVM) is then used to classify the summarized documents and the ones processed by CHI. The classification indicators (precision, recall, and accuracy) achieved by text summarization are higher than the ones achieved by CHI. However, text summarization has negligible higher execution time.

Güran, Aysun (Dogus Author) -- Uysal, Mitat (Dogus Author) This study proposes a novel additive Fuzzy Analytical Hierarchy Process (FAHP) based sentence score function for Automatic Text Summarization (ATS), which is a method to handle growing amounts of textual data. ATS aims to reduce the size of a text while covering the important points in the text. For this aim, this study uses some sentence features, combines these features by an additive score function using some specific weights and produces a sentence score function. The weights of the features are determined by FAHP - specifically Fuzzy Extend Analysis (FEA), which allows the human involvement in the process, uses pair-wise comparisons, addresses uncertainty and allows a hierarchy composed of main features and sub-features. The sentences are ranked according to their score function values and the highest scored sentences are extracted to create summary documents. Performance evaluation is based on the sentence coverage among the summaries generated by human and the proposed method. In order to see the performance of the proposed system, two different Turkish datasets are used and as a performance measure, the F-measure is used. The proposed method is compared with a heuristic algorithm, namely Genetic Algorithm (GA). Resulting performance improvements show that the proposed model will be useful for both researchers and practitioners working in this research area.

Popularity and availability of opinion-rich resources in e-commerce platform is growing rapidly. Before buying any product, one is interested to know the opinion of other people about that product. For any product, there are hundreds of reviews available online so it becomes very difficult for the customers to read all the reviews. Also, one cannot set his mind based on reading some of the review since it gives him a biased view about that product. So we need to automate this process. As we know, there are lots of opinion words present in the sentences of a review which will tell about the polarity of that product. Out of all the opinion words, some words behave in the same manner means they have the same polarity in all contexts, but some words are context dependent means they have different polarity in different context. In this paper, we proposed an Aspect Based Sentiment Analysis and Summarization (ASAS) System, which handles the context dependent opinion words that has been the cause of major difficulties. For finding the opinion polarity, first, we used an online dictionary for classifying the context independent opinion word. Second, we used natural linguistic rules for assigning the polarity to maximum possible context dependent words. These steps create the training data set. Third, for classification of the remaining opinion words, we used opinion words and feature together rather than opinion words alone, because the same opinion word can have different polarity in the same domain. Then we used our Interaction Information method to classify the feature-opinion pairs. Fourth, as negation plays a very crucial role, we found negation words and flipped the polarity of the corresponding opinion word. Finally, after classifying each opinion word, the system generated a short summary for that particular product based on each feature

Text Summarization atau peringkas text merupakan salah satu penerapan Artificial Intelligence (AI) dimana komputer dapat meringkas text pada suatu kalimat atau artikel menjadi lebih sederhana dengan tujuan untuk mempermudah manusia dalam mengambil kesimpulan dari artikel yang panjang tanpa harus membaca secara keseluruhan. Peringkasan teks secara otomatis dengan menggunakan teknik Abstraktif memiliki kemampuan meringkas teks lebih natural sebagaimana manusia meringkas dibandingkan dengan teknik ekstraktif yang hanya menyusun kalimat berdasarkan frekuensi kemunculan kata. Untuk dapat menghasilkan sistem peringkas teks dengan metode abstraktif, membutuhkan metode Recurrent Neural Network (RNN) yang memiliki sistematika perhitungan bobot secara berulang. RNN merupakan bagian dari Deep Learning dimana nilai akurasi yang dihasilkan dapat lebih baik dibandingkan dengan jaringan saraf tiruan sederhana karena bobot yang dihitung akan lebih akurat mendekati persamaan setiap kata. Jenis RNN yang digunakan adalah LSTM (Long Short Term Memory) untuk menutupi kekurangan pada RNN yang tidak dapat menyimpan memori untuk dipilah dan menambahkan mekanisme Attention agar setiap kata dapat lebih fokus pada konteks. Penelitian ini menguji performa sistem menggunakan Precision, Recall, dan F-Measure dengan membandingan hasil ringkasan yang dihasilkan oleh sistem dan ringkasan yang dibuat oleh manusia. Dataset yang digunakan adalah data artikel berita dengan jumlah total artikel sebanyak 4515 buah artikel. Pengujian dibagi berdasarkan data dengan menggunakan Stemming dan dengan teknik Non-stemming. Nilai rata-rata recall artikel berita non-stemming adalah sebesar 41%, precision sebesar 81%, dan F-measure sebesar 54,27%. Sedangkan nilai rata-rata recall artikel berita dengan teknik stemming sebesar 44%, precision sebesar 88%, dan F-measure sebesar 58,20 %.AbstractText Summarization is the application of Artificial Intelligence (AI) where the computer can summarize text of article to make it easier for humans to draw conclusions from long articles without having to read entirely. Abstractive techniques has ability to summarize the text more naturally as humans summarize. The summary results from abstractive techinques are more in context when compared to extractive techniques which only arrange sentences based on the frequency of occurrence of the word. To be able to produce a text summarization system with an abstractive techniques, it is required Deep Learning by using the Recurrent Neural Network (RNN) rather than simple Artificial Neural Network (ANN) method which has a systematic calculation of weight repeatedly in order to improve accuracy. The type of RNN used is LSTM (Long Short Term Memory) to cover the shortcomings of the RNN which cannot store memory to be sorted and add an Attention mechanism so that each word can focus more on the context.This study examines the performance of Precision, Recall, and F-Measure from the comparison of the summary results produced by the system and summaries made by humans. The dataset used is news article data with 4515 articles. Testing was divided based on data using Stemming and Non-stemming techniques. The average recall value of non-stemming news articles is 41%, precision is 81%, and F-measure is 54.27%. While the average value of recall of news articles with stemming technique is 44%, precision is 88%, and F-measure is 58.20%.

In this paper, we describe the design and evaluation of extractive summarization approach to assist the learners with reading difficulties. As existing summarization approaches inherently assign more weights to the important sentences, our approach predicts the summary sentences that are important as well as readable to the target audience with good accuracy. We used supervised machine learning technique for summary extraction of science and social subjects in the educational text. Various independent features from the existing literature for predicting important sentences and proposed learner dependent features for predicting readable sentences are extracted from texts and are used for automatic classification. We performed both extrinsic and intrinsic evaluation on this approach and the intrinsic evaluation is carried out using F-measure and readability analysis. The extrinsic evaluation comprises of learner feedback using likert scale and the effect of assistive summary on improving readability for learners’ with reading difficulty using ANOVA. The results show significant improvement in readability for the target audience using assistive summary.

The exponential increase of subjective, user-generated content since the birth of the Social Web, has led to the necessity of developing automatic text processing systems able to extract, process and present relevant knowledge. In this paper, we tackle the Opinion Retrieval, Mining and Summarization task, by proposing a unified framework, composed of three crucial components (information retrieval, opinion mining and text summarization) that allow the retrieval, classification and summarization of subjective information. An extensive analysis is conducted, where different configurations of the framework are suggested and analyzed, in order to determine which is the best one, and under which conditions. The evaluation carried out and the results obtained show the appropriateness of the individual components, as well as the framework as a whole. By achieving an improvement over 10% compared to the state-of-the-art approaches in the context of blogs, we can conclude that subjective text can be efficiently dealt with by means of our proposed framework. This research work has been funded by the Spanish Government through the project TEXT-MESS 2.0 (TIN2009-13391-C04) and by the Valencian Government through projects PROMETEO (PROMETEO/2009/199) and ACOMP/2011/001.

Contextual advertising is a type of Web advertising, which, given the URL of a Web page, aims to embed into the page the most relevant textual ads available. For static pages that are displayed repeatedly, the matching of ads can be based on prior analysis of their entire content; however, often ads need to be matched to new or dynamically created pages that cannot be processed ahead of time. Analyzing the entire content of such pages on-the-fly entails prohibitive communication and latency costs. To solve the three-horned dilemma of either low relevance or high latency or high load, we propose to use text summarization techniques paired with external knowledge (exogenous to the page) to craft short page summaries in real time. Empirical evaluation proves that matching ads on the basis of such summaries does not sacrifice relevance, and is competitive with matching based on the entire page content. Specifically, we found that analyzing a carefully selected 6% fraction of the page text can sacrifice only 1%--3% in ad relevance. Furthermore, our summaries are fully compatible with the standard JavaScript mechanisms used for ad placement: they can be produced at ad-display time by simple additions to the usual script, and they only add 500--600 bytes to the usual request. We also compared our summarization approach, which is based on structural properties of the HTML content of the page, with a more principled one based on one of the standard text summarization tools (MEAD), and found their performance to be comparable.

In this paper, we present a system called QueSTS, which generates a query specific extractive summary of a selected set of documents. We have proposed an integrated graph approach to represent the contextual relationships among sentences of all the input documents. These relationships are exploited and several sub-graphs of the integrated graph are constructed. These sub-graphs consist of sentences that are highly relevant to the query and that are highly related to each other. These sub-graphs are ranked by a scoring model. The highest ranked sub-graph which is rich in query relevant information is selected as a query specific summary. A sentence ordering strategy has also been proposed by us to improve the coherence of the summary. Sentences in the selected summary are sequenced as per the above strategy. Experimental results show that the summaries generated by the QueSTS system are significantly better than other systems in terms of user satisfaction. � 2010 World Scientific Publishing Company.

In this paper, we propose a generic text summarization method that generates summaries of Turkish texts by ranking sentences according to their scores. Sentence scores are calculated using their surface-level features, and summaries are created by extracting the highest ranked sentences from the original documents. To extract sentences which form a summary with an extensive coverage of the main content of the text and less redundancy, we use features such as term frequency, key phrase (KP), centrality, title similarity and sentence position. The sentence rank is computed using a score function that uses its feature values and the weights of the features. The best feature weights are learned using machine-learning techniques with the help of human-constructed summaries. Performance evaluation is conducted by comparing summarization outputs with manual summaries of two newly created Turkish data sets. This paper presents one of the first Turkish summarization systems, and its results are promising. We introduce the usage of KP as a surface-level feature in text summarization, and we show the effectiveness of the centrality feature in text summarization. The effectiveness of the features in Turkish text summarization is also analyzed in detail. © The Author 2008. Published by Oxford University Press on behalf of The British Computer Society. All rights reserved.

Text summarization is a process of distilling the most important content from text documents. While human beings have proven to be extremely capable summarizers, computer based automatic abstracting and summarizing has proven to be extremely challenging tasks. In this paper we report our experience with applying extractive summarization techniques to process news articles, economic reports and nursing narratives. We present analysis of the effect of different summarization methods and parameters on the summarization results. We also compare the performance of the summarizers across the three different document genres. The learned lessons are discussed and the possibilities for applying the theory of Computing with Words in text summarization are elaborated.

The Web 2.0 has resulted in a shift as to how users consume and interact with the information, and has introduced a wide range of new textual genres, such as reviews or microblogs, through which users communicate, exchange, and share opinions. The exploitation of all this user-generated content is of great value both for users and companies, in order to assist them in their decision-making processes. Given this context, the analysis and development of automatic methods that can help manage online information in a quicker manner are needed. Therefore, this article proposes and evaluates a novel concept-level approach for ultra-concise opinion abstractive summarization. Our approach is characterized by the integration of syntactic sentence simplification, sentence regeneration and internal concept representation into the summarization process, thus being able to generate abstractive summaries, which is one the most challenging issues for this task. In order to be able to analyze different settings for our approach, the use of the sentence regeneration module was made optional, leading to two different versions of the system (one with sentence regeneration and one without). For testing them, a corpus of 400 English texts, gathered from reviews and tweets belonging to two different domains, was used. Although both versions were shown to be reliable methods for generating this type of summaries, the results obtained indicate that the version without sentence regeneration yielded to better results, improving the results of a number of state-of-the-art systems by 9%, whereas the version with sentence regeneration proved to be more robust to noisy data. This research work has been partially funded by the University of Alicante, Generalitat Valenciana, Spanish Government and the European Commission through the projects, “Tratamiento inteligente de la información para la ayuda a la toma de decisiones” (GRE12-44), “Explotación y tratamiento de la información disponible en Internet para la anotación y generación de textos adaptados al usuario” (GRE13-15), DIIM2.0 (PROMETEOII/2014/001), ATTOS (TIN2012-38536-C03-03), LEGOLANG-UAGE (TIN2012-31224), SAM (FP7-611312), and FIRST (FP7-287607).

Text summarization namely, automatically generating a short summary of a given document, is a difficult task in natural language processing. Nowadays, deep learning as a new technique has gradually been deployed for text summarization, but there is still a lack of large-scale high quality datasets for this technique. In this paper, we proposed a novel deep learning method to identify high quality document–summary pairs for building a large-scale pairs dataset. Concretely, a long short-term memory (LSTM)-based model was designed to measure the quality of document–summary pairs. In order to leverage information across all parts of each document, we further proposed an improved LSTM-based model by removing the forget gate in the LSTM unit. Experiments conducted on the training set and the test set built upon Sina Weibo (a Chinese microblog website similar to Twitter) showed that the LSTM-based models significantly outperformed baseline models with regard to the area under receiver operating characteristic curve (AUC) value.

In this paper we propose a general framework for topic-specific summarization of large text corpora and illustrate how it can be used for the analysis of news databases. Our framework, concise comparative summarization (CCS), is built on sparse classification methods. CCS is a lightweight and flexible tool that offers a compromise between simple word frequency based methods currently in wide use and more heavyweight, model-intensive methods such as latent Dirichlet allocation (LDA). We argue that sparse methods have much to offer for text analysis and hope CCS opens the door for a new branch of research in this important field. For a particular topic of interest (e.g., China or energy), CSS automatically labels documents as being either on- or off-topic (usually via keyword search), and then uses sparse classification methods to predict these labels with the high-dimensional counts of all the other words and phrases in the documents. The resulting small set of phrases found as predictive are then harvested as the summary. To validate our tool, we, using news articles from the New York Times international section, designed and conducted a human survey to compare the different summarizers with human understanding. We demonstrate our approach with two case studies, a media analysis of the framing of "Egypt" in the New York Times throughout the Arab Spring and an informal comparison of the New York Times' and Wall Street Journal's coverage of "energy." Overall, we find that the Lasso with $L^2$ normalization can be effectively and usefully used to summarize large corpora, regardless of document size., Comment: Published in at http://dx.doi.org/10.1214/13-AOAS698 the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org)