Search

Feedback is important to improve writing quality; however, to provide timely and personalized feedback is a time-intensive task. Currently, most literature focuses on providing (human or machine) support on product characteristics, especially after a draft is submitted. However, this does not assist students who struggle during the writing process. Therefore, in this study, we investigate the use of keystroke analysis to predict writing quality throughout the writing process. Keystroke data were analyzed from 126 English as a second language learners performing a timed academic summarization task. Writing quality was measured using participants’ final grade. Based on previous literature, 54 keystroke features were extracted. Correlational analyses were conducted to identify the relationship between keystroke features and writing quality. Next, machine learning models (regression and classification) were used to predict final grade and classify students who might need support at several points during the writing process. The results show that, in contrast to previous work, the relationship between writing quality and keystroke data was rather limited. None of the regression models outperformed the baseline, and the classification models were only slightly better than the majority class baseline (highest AUC = 0.57). In addition, the relationship between keystroke features and writing quality changed throughout the course of the writing process. To conclude, the relationship between keystroke data and writing quality might be less clear than previously posited.

Short text clustering has far-reaching effects on semantic analysis, showing its importance for multiple applications such as corpus summarization and information retrieval. However, it inevitably encounters the severe sparsity of short text representations, making the previous clustering approaches still far from satisfactory. In this paper, we present a novel attentive representation learning model for shot text clustering, wherein cluster-level attention is proposed to capture the correlations between text representations and cluster representations. Relying on this, the representation learning and clustering for short texts are seamlessly integrated into a unified model. To further ensure robust model training for short texts, we apply adversarial training to the unsupervised clustering setting, by injecting perturbations into the cluster representations. The model parameters and perturbations are optimized alternately through a minimax game. Extensive experiments on four real-world short text datasets demonstrate the superiority of the proposed model over several strong competitors, verifying that robust adversarial training yields substantial performance gains., Comment: 14pages, to appear in IEEE TKDE

In this paper, we propose a novel deep Efficient Relational Sentence Ordering Network (referred to as ERSON) by leveraging pre-trained language model in both encoder and decoder architectures to strengthen the coherence modeling of the entire model. Specifically, we first introduce a divide-and-fuse BERT (referred to as DF-BERT), a new refactor of BERT network, where lower layers in the improved model encode each sentence in the paragraph independently, which are shared by different sentence pairs, and the higher layers learn the cross-attention between sentence pairs jointly. It enables us to capture the semantic concepts and contextual information between the sentences of the paragraph, while significantly reducing the runtime and memory consumption without sacrificing the model performance. Besides, a Relational Pointer Decoder (referred to as RPD) is developed, which utilizes the pre-trained Next Sentence Prediction (NSP) task of BERT to capture the useful relative ordering information between sentences to enhance the order predictions. In addition, a variety of knowledge distillation based losses are added as auxiliary supervision to further improve the ordering performance. The extensive evaluations on Sentence Ordering, Order Discrimination, and Multi-Document Summarization tasks show the superiority of ERSON to the state-of-the-art ordering methods.

In a cluster of news texts on the same event, two sentences from different documents might express different multi-document phenomena (redundancy, complementarity, and contradiction). Cross-Document Structure Theory (CST) provides labels to explicitly represent these phenomena. The automatic identification of the multi-document phenomena and their correspondent CST relations is definitely handy for Automatic Multi-Document Summarization since it helps computers understand text meaning. In this paper, we evaluated a typology of (textual) signals for the automatic detection of the CST relations of complementarity (i.e., Historical background, Follow-up and Elaboration) in a multi-document corpus of news texts in Brazilian Portuguese. Using algorithms from different machine-learning paradigms, we obtained classifiers that achieved high general accuracy (higher than 90%), indicating the potential of the signals. Em uma coleção de notícias sobre um mesmo evento, duas sentenças de textos distintos podem expressar diferentes fenômenos multidocumento (redundância, complementaridade e contradição). A Cross-Document Structure Theory (CST) provê rótulos para representar esses fenômenos. A identificação automática dos fenômenos multidocumento e das relações CST correspondentes é central à Sumarização Automática Mutidocumento, pois ajuda a máquina a entender o conteúdo textual. Neste artigo, avaliou-se uma tipologia de sinais (textuais) para a detecção automática das relações CST de complementaridade (Historical background, Follow-up e Elaboration) em um corpus multidocumento de notícias em Português do Brasil. Utilizando algoritmos de diferentes paradigmas de Aprendizado de Máquina, obtiveram-se classificadores que atingiram alto índice de acurácia geral (superior a 90%), indicando o potencial dos sinais.

Logs contain valuable information about the runtime behaviors of software systems. Thus, practitioners rely on logs for various tasks such as debugging, system comprehension, and anomaly detection. However, due to the unstructured nature and large size of logs, there are several challenges that practitioners face with log analysis. In this paper, we propose a novel approach called LogAssist that tackles these challenges and assists practitioners with log analysis. LogAssist provides an organized and concise view of logs by first grouping logs into event sequences (i.e., workflows), which better illustrate the system runtime execution paths. Then, LogAssist compresses the log events in workflows by hiding consecutive events and applying n-gram modeling to identify common event sequences. We evaluated LogAssist on the logs that are generated by two open-source and one enterprise system. We find that LogAssist can reduce the number of log events that practitioners need to investigate by up to 99%. Through a user study with 19 participants, we also find that LogAssist can assist practitioners by reducing the needed time on log analysis tasks by an average of 40%. The participants also rated LogAssist an average of 4.53 out of 5 for improving their experiences of performing log analysis. Finally, we document our experiences and lessons learned from developing and adopting LogAssist in practice. We believe that LogAssist and our reported experiences may lay the basis for future analysis and interactive exploration on logs.

Extracting relevant information from a large amount of data is a challenging task. Automatic text summarization is a potential solution for obtaining this information. In this paper, a nature inspired swarm intelligence-based algorithm viz. firefly algorithm for multi-document text summarization is proposed. A new fitness function consisting of three features viz. topic relation factor, cohesion factor and readability factor is utilized. The experiments are performed on datasets from Document Understanding Conference i.e. DUC-2002, DUC-2003 and DUC-2004. The performance of the algorithm has been evaluated using ROUGE score. The performance of the proposed algorithm is compared with some other nature inspired ones such as particle swarm optimization (PSO) and genetic algorithm (GA). The performance of the proposed algorithm outperforms the other adopted ones.

In the natural language processing family, learning representations is a pioneering study, especially in sequence-to-sequence tasks where outputs are generated, totally relying on the learning representations of source sequence. Generally, classic methods infer that each word occurring in the source sequence, having more or less influence on the target sequence, should all be considered when generating outputs. As the summarization task requires the output sequence to only retain the essence, classic full consideration of the source sequence may not work well on it, which calls for more suitable methods with the ability to discard the misleading noise words. Motivated by this, with both relevance retaining and redundancy removal in mind, we propose a summarization learning model by implementing an encoder with copious contextual information represented and a decoder with a selecting mechanism integrated. Specifically, we equip the encoder with an asynchronous bi directional parallel structure, in order to obtain abundant semantic representation. The decoder, different from the classic attention-based works, employs a self-aware context selecting mechanism to generate summary in a more productive way. We evaluate the proposed methods on three benchmark summarization corpora. The experimental results demonstrate the effectiveness and applicability of the proposed framework in relation to several well-practiced and state-of-the-art summarization methods.

The day-to-day growth of online information necessitates intensive research in automatic text summarization (ATS). The ATS software produces summary text by extracting important information from the original text. With the help of summaries, users can easily read and understand the documents of interest. Most of the approaches for ATS used only local properties of text. Moreover, the numerous properties make the sentence selection difficult and complicated. So this article uses a graph based summarization to utilize structural and global properties of text. It introduces maximal clique based sentence selection (MCBSS) algorithm to select important and non-redundant sentences that cover all concepts of the input text for summary. The MCBSS algorithm finds novel information using maximal cliques (MCs). The experimental results of recall oriented understudy for gisting evaluation (ROUGE) on Timeline dataset show that the proposed work outperforms the existing graph algorithms Bushy Path (BP), Aggregate Similarity (AS), and TextRank (TR).

In the era of social networks, the rapid growth of data mining in information retrieval and natural language processing makes automatic text summarization necessary. Currently, pretrained word embedding and sequence to sequence models can be effectively adapted in social network summarization to extract significant information with strong encoding capability. However, how to tackle the long text dependence and utilize the latent topic mapping has become an increasingly crucial challenge for these models. In this article, we propose a topic-aware extractive and abstractive summarization model named T-BERTSum, based on Bidirectional Encoder Representations from Transformers (BERTs). This is an improvement over previous models, in which the proposed approach can simultaneously infer topics and generate summarization from social texts. First, the encoded latent topic representation, through the neural topic model (NTM), is matched with the embedded representation of BERT, to guide the generation with the topic. Second, the long-term dependencies are learned through the transformer network to jointly explore topic inference and text summarization in an end-to-end manner. Third, the long short-term memory (LSTM) network layers are stacked on the extractive model to capture sequence timing information, and the effective information is further filtered on the abstractive model through a gated network. In addition, a two-stage extractive-abstractive model is constructed to share the information. Compared with the previous work, the proposed model T-BERTSum focuses on pretrained external knowledge and topic mining to capture more accurate contextual representations. Experimental results on the CNN/Daily mail and XSum datasets demonstrate that our proposed model achieves new state-of-the-art results while generating consistent topics compared with the most advanced method.

Update summarization is a relatively recent summarization task concerned with creating a short summary from news articles, assuming the user has already read a number of previous articles. It is useful for users who want to know the latest information about a specific topic. The availability of systems that provide update summaries saves user time and effort. Unfortunately, such resources are lacking for the Arabic language. This paper aims to provide an update summarization system that generates an update summary containing the latest information requested by a user from multiple documents. This paper provides an Arabic query-based Update-Summarization System (AUSS). We use a graph-based ranking model to represent the similarity, through a combination of lexical and semantic relations between words. Our experiments show that AUSS achieves promising results, achieving a best F-Measure of 0.5405. To test AUSS, we created a new corpus especially for Arabic Update Summaries, which we call (AUS-DB). AUS-DB contains 183 articles and their corresponding reference summaries.

The availability of legal judgment documents in digital form offers numerous opportunities for information extraction and application. Automatic summarization of these legal texts is a crucial and a challenging task due to the unusual structure and high complexity of these documents. Previous approaches in this direction have relied on huge labelled datasets, using hand engineered features, leveraging on domain knowledge and focussed their attention on a narrow sub-domain for increased effectiveness. In this paper, we propose simple generic techniques using neural network for the summarization task for Indian legal judgment documents. We explore two neural network architectures for this task utilizing the word and sentence embeddings for capturing the semantics. The main advantage of the proposed approaches is that they do not rely on hand crafted features, or domain specific knowledge, nor is their application restricted to a particular sub-domain thus making them suitable to be extended to other domains as well. We tackle the problem of unavailability of labelled data for the task by assigning classes/scores to sentences in the training set, based on their match with reference summary produced by humans. The experimental evaluations establish the effectiveness of our proposed approaches as compared with other baselines.

Document clustering has recently been paid great attention in retrieval, navigation, and summarization of huge volumes of documents. With a better document clustering approach, computers can organize a document corpus automatically to a meaningful cluster for enabling efficient navigation, and browsing of the corpus. Document navigation and browsing is a valuable complement to the deficiencies of information retrieval technologies. This paper introduces Modsup-based frequent itemset and Rider Optimization-based Moth Search Algorithm (Rn-MSA) for clustering the documents. At first, the input documents are given to the pre-processing step, and then, the extraction is carried out based on TF-IDF and Wordnet features. Once the extraction is done, the feature selection is carried out based on frequent itemset for the establishment of feature knowledge. At last, the document clustering is done using the proposed Rn-MSA, which is designed by combining Rider Optimization Algorithm (ROA), and the Moth Search Algorithm (MSA). The performance of the document clustering based on proposed Modsup + Rn-MSA is evaluated in terms of precision, recall, F-Measure, and accuracy. The developed document clustering method achieves the maximal precision of 95.90%, maximal recall of 96.41%, maximal F-Measure of 96.41%, and the maximal accuracy of 95.12% that indicates its superiority.

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.

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.

Article is devoted to a method of automatic text summarization of the legal information provided in Chinese. The model of the legal document abstract and the procedure of his formation is considered. To determine the level of importance of sentences, it was suggested to proceed to determine the weight values of separate hieroglyphs, rather than words in the text of documents and abstracts. Also consideration of model of documents as networks of sentences for detection of the most important sentences on parameters of this network was offered., Роботу присвячено методу автоматичного реферування правової інформації КНР, представленої китайською мовою. Розглянуто модель реферату правового документа і принципи його формування. Для вирішення завдання визначення рівня важливості речень з вихідного документа було запропоновано перейти до визначення вагових значень окремих ієрогліфів, а не слів в тексті документів і рефератів.

Extraction of knowledge from soccer videos has enormous applications like context-based advertisement, content-based video retrieval, match summarization, and highlight extraction. Overlapping soccer actions and uncontrolled video capturing conditions make it challenging to detect action accurately. For overcoming these problems, Convolutional Neural Network and Recurrent Neural Network are used jointly to classify different lengths of soccer actions. Initially, transfer learning from pre-trained VGG network extracts characteristic spatial features. Afterwards, Gated Recurrent Unit deals with temporal dependency and solves the vanishing gradient problem. Finally, softmax layer assigns decimal probabilities to each class. Experimental results demystify the significance of the proposed architecture.

With the explosive growth of videos captured everyday, how to efficiently extract useful information from videos has become a more and more important problem. As one of the most effective methods, video summarization aiming to extract the most important frames or shots has attracted more interests recently. Currently, lots of methods employ a recurrent structure. However, due to its step-by-step characteristic, it is difficult to parallelize these models. To address this problem, we propose a dual-path attentive video summarization framework consisting of a temporal spatial encoder, a score-aware encoder and a decoder. And all of them are mainly based on multi-head self-attention and convolutional block attention module. The temporal spatial encoder is to capture the temporal and spatial information while the score-aware encoder incorporates the appearance features with previously predicted frame-level importance scores. By combining the scores and appearance features, our model can better capture the long-range global dependencies and update the importance scores of previous frames continuously. Moreover, entirely based on attention mechanism, our model can be trained in full parallel, which leads to less training time. To validate the method, we employ the two popular datasets SumMe and TVSum. The experimental results show the effectiveness of the proposed method.

Although video summarization has achieved tremendous success benefiting from Recurrent Neural Networks (RNN), RNN-based methods neglect the global dependencies and multi-hop relationships among video frames, which limits the performance. Transformer is an effective model to deal with this problem, and surpasses RNN-based methods in several sequence modeling tasks, such as machine translation, video captioning, etc. Motivated by the great success of transformer and the natural structure of video (frame-shot-video), a hierarchical transformer is developed for video summarization, which can capture the dependencies among frame and shots, and summarize the video by exploiting the scene information formed by shots. Furthermore, we argue that both the audio and visual information are essential for the video summarization task. To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer. In this paper, the proposed method is denoted as Hierarchical Multimodal Transformer (HMT). Practically, extensive experiments show that HMT achieves (F-measure: 0.441, Kendall’s τ : 0.079, Spearman’s ρ : 0.080) and (F-measure: 0.601, Kendall’s τ : 0.096, Spearman’s ρ : 0.107) on SumMe and TVsum, respectively. It surpasses most of the traditional, RNN-based and attention-based video summarization methods.

Ever since the first introduction of Artificial Intelligence into the field of hydrology, it has further generated immense interest in researching aspects for further improvements to hydrology. This can be seen in the rising number of related works published. This culminated further with the combination of pioneering optimization techniques. Who would have thought that the birds and the bees can offer advances in the mathematical sciences and so have the ants too? The ingenuity of humans is spelled out in the algorithms that mimic many natural activities, like pack hunting by the wolves! This review paper serves to broadcast more of the intriguing interest in newfound procedures in optimal forecasting. Reservoirs are the main and most efficient water storage facilities for managing uneven water distribution. However, due to the major global climate changes which affect rainfall trend and weather, it has been a necessity to find an alternative solution for effective conventional water balance. A multifunctional reservoir operation appears to require the operator to make wise decisions to achieve an optimal reservoir operation. One of the most important aspects of all this is the forecasting of streamflows. For this, Artificial Intelligence (AI) seems to be the best alternative solution; as in the past three decades, there has been a drastic increase in building and developing AI models for forecasting and modelling unstable patterns in various hydrological fields. Nevertheless, AI models are also required to be optimized in tandem to achieve the best result, leading thus to the desirous forming of hybrid models between a standalone AI model and optimization techniques. This comprehensive study categorizes machine learning into three main categories, together with the optimization techniques, and will next explore the various AI model used for different hydrology fields along with the most common optimization techniques. Summarization of findings under every section is provided. Some advantages and disadvantages found through literature reviews are summarized for ease of reference. Finally, future recommendations and overall conclusions drawn from the results of researchers are included. This current review focuses on papers from high-impact factor publications based on 10 years starting from (2009 to 2020).

3D printing or additive manufacturing process works on the stereolithographic process. It is based on the x, y and z-axis whereas in 4D printing another dimension is added which is time and with the combination of smart material alteration in shape, properties and function are possible under the corresponding external stimulus. The shape-shifting behaviour of 4D printed objects gives it an edge over 3D printing but it has a limitation of producing objects having curved layers and requiring higher strength. The concepts and applicability of 5D printing (5DP) are discussed. Summarization of the 3D and 4D printing process along with their limitations are also presented. The limitation of 3D and 4D printing of not printing those structures or complex shapes which require higher strength or have a curve layer can be printed with 5D printing. In the case of 5DP, there are two additional axes i.e. rotation of print bed and rotation of extruder head. In this study detailed process, general application and a case study of 5DP in the healthcare and medical industry focussed on dental surgery and orthopaedics is summarized.

Code summarization (aka comment generation) provides a high-level natural language description of the function performed by code, which can benefit the software maintenance, code categorization and retrieval. To the best of our knowledge, the state-of-the-art approaches follow an encoder-decoder framework which encodes source code into a hidden space and later decodes it into a natural language space. Such approaches suffer from the following drawbacks: (a) they are mainly input by representing code as a sequence of tokens while ignoring code hierarchy; (b) most of the encoders only input simple features (e.g., tokens) while ignoring the features that can help capture the correlations between comments and code; (c) the decoders are typically trained to predict subsequent words by maximizing the likelihood of subsequent ground truth words, while in real world, they are excepted to generate the entire word sequence from scratch. As a result, such drawbacks lead to inferior and inconsistent comment generation accuracy. To address the above limitations, this paper presents a new code summarization approach using hierarchical attention network by incorporating multiple code features, including type-augmented abstract syntax trees and program control flows. Such features, along with plain code sequences, are injected into a deep reinforcement learning (DRL) framework (e.g., actor-critic network) for comment generation. Our approach assigns weights (pays “attention”) to tokens and statements when constructing the code representation to reflect the hierarchical code structure under different contexts regarding code features (e.g., control flows and abstract syntax trees). Our reinforcement learning mechanism further strengthens the prediction results through the actor network and the critic network, where the actor network provides the confidence of predicting subsequent words based on the current state, and the critic network computes the reward values of all the possible extensions of the current state to provide global guidance for explorations. Eventually, we employ an advantage reward to train both networks and conduct a set of experiments on a real-world dataset. The experimental results demonstrate that our approach outperforms the baselines by around 22% to 45% in BLEU-1 and outperforms the state-of-the-art approaches by around 5% to 60% in terms of S-BLEU and C-BLEU.