Search

Recently, for the abstractive summarization task, most of proposed techniques have adopted the deep recurrent neural network (RNN)-based sequential auto-encoding architecture to effectively learn and generate meaningful summaries for different input documents. However, most of recent RNN-based models always suffer the challenges related to the involvement of much capturing high-frequency/reparative phrases in long documents during the training process which leads to the outcome of trivial and generic summaries are generated. In addition, the lack of thorough analysis on the sequential and long-range dependency relationships between words within different contexts while learning the textual representation also makes the achieved summaries unnatural and incoherent. In order to deal with these challenges, in this paper we proposed a novel semantic-enhanced generative adversarial network (GAN)-based approach for abstractive text summarization task, called as: SGAN4AbSum. We use an adversarial training strategy for our text summarization model which trains the generator and discriminator to simultaneously handle the summary generation and distinguishing the generated summary with the ground-truth one. The input of generator is the jointed rich-semantic and global structural latent representations of training documents which are achieved by applying a combined BERT and graph convolutional network textual embedding mechanism. Extensive experiments in benchmark datasets demonstrate the effectiveness of our proposed SGAN4AbSum which achieve the competitive ROUGE-based scores in comparing with state-of-the-art abstractive text summarization baselines. [ABSTRACT FROM AUTHOR]

Text summarization is the process of converting the input document into a short form, provided that it preserves the overall meaning associated with it. Primarily, text summarization is achieved in two ways, i.e., abstractive and extractive. Extractive summarizers select a few best sentences out of the input document, while abstractive methods may modify the sentence structure or introduce new sentences. The proposed approach is an extractive text summarization technique, where we have expanded topic modeling specifically to be applied to multiple lower-level specialized entities (i.e., groups) embedded in a single document. Our goal is to overcome the lack of coherence issues found in the summarization techniques. Topic modeling was initially proposed to model text data at the multi-document and word levels without considering sentence modeling. Subsequently, it has been applied at the sentence level and used for the document summarization; however, certain limitations were associated. Topic modeling does not perform as expected when applied to a single document at the sentence level. To address this shortcoming, we have proposed a summarization approach that is incorporated at the individual document and clusters level (instead of the sentence level). We aim to choose the best statement from each group (containing sentences of the same kind) found in the given text. We have tried to select the perfect topic by evaluating the probability distribution of the words and respective topics' at the cluster level. The method is evaluated on two standard datasets and shows significant performance gains over existing text summarization techniques. Compared to other text summarization techniques, the Rouge parameters for automatic evaluation show a considerable improvement in F-measure, precision, and recall of the generated summary. Furthermore, a manual evaluation has demonstrated that the proposed approach outperforms the current state-of-the-art text summarization approaches. [ABSTRACT FROM AUTHOR]

In the past few decades, the automatic text summarization process has become an essential area in research. The automatic text summarization process extracts the essential and the most-resourceful information the users need, and various users in many fields easily handle it. This work extracts linear and non-linear information using a Support Vector Machine (SVM). Then, the extracted features are given into the Bag of Features (BoF) which is provided as an input to the classifier model known as Multi-layered CNN for feature representation. This process is known as BoF-CNN. The multiple layers of the CNN model analyse the given features and provide the weighted score for the keywords based on the higher needs. The importance/classification is provided. The combinations of features are weighted with the graph model when placed in BoF. The proposed model effectively analyses the features and classifies the text based on weight. The simulation is done in MATLAB 2020a environment and provides better results when analysing incoming data. [ABSTRACT FROM AUTHOR]

Having control over your data is a right and a duty that every citizen has in our digital society. It is often that users skip entire policies of applications or websites to save time and energy without realizing the potential sticky points in these policies. Due to obscure language and verbose explanations majority of users of hypermedia do not bother to read them. Further, sometimes digital media companies do not spend enough effort in stating their policies clearly which often time can also be incomplete. A summarized version of these privacy policies that can be categorized into the useful information can help the users. To solve this problem, in this work we propose to use machine learning-based models for policy categorizer that classifies the policy paragraphs under the attributes proposed like security, contact, etc. By benchmarking different machine learning-based classifier models, we show that artificial neural network model performs with higher accuracy on a challenging dataset of textual privacy policies. We thus show that machine learning can help summarize the relevant paragraphs under the various attributes so that the user can get the gist of that topic within a few lines. [ABSTRACT FROM AUTHOR]