Enhancing E-Business-Intelligence-Service: A Topic-Guided Text Summarization Framework

Text summarization is an emerging technique for finding out the summary of the text document. Text summarization is nothing but summarizing the content of given text document. Text summarization has got so uses such as Due to the massive amount of information getting increased on internet; it is difficult for the user to go through all the information available on web. Summarization techniques need to be used to reduce the user's time in reading the whole information available on web. In this paper, we propose an automatic text summarization technique using both linguistic and statistical features using successive threshold for finding the summary i.e important sentences from the given input text document. Here the sentences are selected for summary based on the weight of the sentence. The weight of the sentences is calculated based on the statistical and linguistic features. Our approach assigns scores to the sentences by weighting the features like term frequency, word occurrences, and noun weight, phrases etc. In our approach, the number of sentences present in our summary would be equal to the number of paragraphs present in a text document, which can be achieved by using our successive threshold approach.

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.

Abstractive text summarization: State of the art, challenges, and improvements

Text summarization is an important problem, which has numerous applications. This problem has been extensively studied and many approaches have been proposed in the literature for its solution. One of the most challenging problems in the field of text summarization is generating a user-focused summary based on a query. In this paper, we investigate a new approach that tackles this problem and proposes a new solution using document graphs. We have employed data from Document Understanding Conference 2006 (DUC-2006).

Text summarization is an approach to summarize the original document with better efficiency than human. Mining prominent words from the original document and connecting those to make a semantically correct sentence in the best way are, the ultimate goal. This paper focuses on making the summary more reliable and understandable with the techniques of fuzzy logic. The extractive method of text summarization and the fuzzy logic method along with algorithms have enhanced the power of unsupervised learning which is proved by comparison with the algorithms working alone.

Abstractive text summarization using sequence-to-sequence networks have been successful for short text. However, these models have shown their limitations in summarizing long text as they forget sentences in long distance. We propose an abstractive summarization model using rich features to overcome this weakness. The proposed system has been tested with two datasets: an English dataset (CNN/Daily Mail) and a Vietnamese dataset (Baomoi). Experimental results show that our model significantly outperforms recently proposed models on both datasets.

Every day, the amount of textual data created increases exponentially, both in terms of complexity and volume. Massive amounts of information are generated by social media, news articles, emails, text messages and other resources, making it difficult to read lengthy language materials. Our main objective in the paper is to obtain a short understandable and fluent abstractive summary of any given text. The Abstractive Text Summarizer automatically gives the summary of the text by generating new phrase, rephrasing or using the new words which are not present in the original text. In this paper, a machine learning architecture i.e. Stacked LSTM based on attention mechanism using Sequence-to-Sequence model is proposed, to generate the summary using abstractive approach for Amazon reviews of fine foods dataset. Our approach allows the model to accept content and provide a concise summary that may clearly describe the gist of the original text. The experiments on Amazon reviews of fine foods dataset show that our model obtained BLEU Score as 0.91 for a test set.

<p indent="0mm">The dataset is the foundation for automatic text summarization, and its quality directly determines the performance of summarization systems. Currently, research on Tibetan text summarization suffers from a lack of publicly available, high-quality open-source datasets, which has constrained progress in this field. To fill this gap, news texts were collected from various Tibetan websites, and human-written summaries were created for each text. Additionally, both subjective and objective evaluation methods were used to comprehensively assess the matching between Tibetan news texts and their corresponding human-written summaries, ensuring the quality of the data. Ultimately, BodSUM-6000, a dataset of high-quality ive Tibetan text summarization consisting of 6,000 text-summary pairs, was constructed. This dataset provides valuable data resources for training and evaluating abstractive Tibetan text summarization models, helping to address the limitations in the generalizability and accuracy of current Tibetan text summarization techniques, and promoting the further development of Tibetan automatic summarization research.

Automatic text summarization is a subarea of natural language processing that generates a summary of the text by keeping its key points. The research work done on summarizing low-resourced language text is very limited. In India, the Hindi language is being spoken by central and north Indian people and only a few research works have been done on abstractive summarization of Hindi language. Having matras in Hindi makes it difficult to tokenize so it is difficult to summarize Hindi text using abstractive text summarization. In the proposed method, abstractive Hindi text summarization is done using transliteration and fine-tuning. In this work, the model is trained to generate both summaries and headlines. ROUGE-score and BERT-score have been utilized to check summary quality. A new semantic similarity score-based performance measure is also proposed to measure semantic similarity between reference summaries and predicted summaries. Using the proposed method, we have achieved the highest 55.16 ROUGE score, 0.80 BERT score, and 0.98 similarity score. Along with these performance measures, human evaluation of predicted summaries is also done and it is found that summaries and headlines were generated at a human-acceptable level.

text summarization is a classic sequence-to-sequence natural language generation task. In order to improve the quality of unsupervised abstract text summarization in unsupervised mode, we propose two constraints for training text summarization model, embedding space constraint and information ratio constraint. We construct a generative adversarial network with two discriminators based on these two constraints (TC-SUM-GAN). We use unsupervised and supervised methods to train the model in the experiment. Experimental results show that the ROUGE-1 value of the unsupervised TC-SUM-GAN increases by [Formula: see text] points compared with the basic model and at least 1.96 points compared with other comparative models. The ROUGE scores of the supervised TC-SUM-GAN are also improved. TC-SUM-GAN achieves very competitive results for the metrics of ROUGE-1 and ROUGE-2. In addition, the abstracts generated by our model are closer to those generated manually.

Dealing with vast amounts of textual data requires the use of efficient systems. Automatic summarization systems are capable of addressing this issue. Therefore, it becomes highly essential to work on the design of existing automatic summarization systems and innovate them to make them capable of meeting the demands of continuously increasing data, based on user needs. This study tends to survey the scientific literature to obtain information and knowledge about the recent research in automatic text summarization specifically abstractive summarization based on neural networks. A review of various neural networks based abstractive summarization models have been presented. The proposed conceptual framework includes five key elements identified as encoder-decoder architecture, mechanisms, training strategies and optimization algorithms, dataset, and evaluation metric. A description of these elements is also included in this article. The purpose of this research is to provide an overall understanding and familiarity with the elements of recent neural networks based abstractive text summarization models with an up-to-date review as well as to render an awareness of the challenges and issues with these systems. Analysis has been performed qualitatively with the help of a concept matrix indicating common trends in the design of recent neural abstractive summarization systems. Models employing a transformer-based encoder-decoder architecture are found to be the new state-of-the-art. Based on the knowledge acquired from the survey, this article suggests the use of pre-trained language models in complement with neural network architecture for abstractive summarization task.

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 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> -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.

Recurrent neural network-based sequence-to-sequence attentional models have proven effective in abstractive text summarization. In this paper, we model abstractive text summarization using a dual encoding model. Different from the previous works only using a single encoder, the proposed method employs a dual encoder including the primary and the secondary encoders. Specifically, the primary encoder conducts coarse encoding in a regular way, while the secondary encoder models the importance of words and generates more fine encoding based on the input raw text and the previously generated output text summarization. The two level encodings are combined and fed into the decoder to generate more diverse summary that can decrease repetition phenomenon for long sequence generation. The experimental results on two challenging datasets (i.e., CNN/DailyMail and DUC 2004) demonstrate that our dual encoding model performs against existing methods.

Text summarization techniques are widely used to generate abstracts of documents automatically, facilitating users to capture the needed information from a large amount of documents. However, it poses a great challenge to satisfy the information needs of users in different roles while keeping the most important information. To solve this problem, we propose a novel framework on text summarization, which incorporates historical information of users to generate a user-oriented personalized summarization. The framework adopts two topic models to model the comments of doctors and patients from health-related social networks about certain diseases, and then identifies topics that the two kinds of users are interested in. Based on the identified topics, we propose three methods for sentence ranking to generate summarizations about the diseases for doctors and patients, respectively. Experimental results show a high similarity between the generated summarization and the real interests of different users, better meeting the information needs while keeping the summarization performance.

In recent years, there has been growing interest in the field of abstractive text summarization with focused contributions in relevant model architectures, datasets, and evaluation metrics. Despite notable research advances, previous works have identified certain limitations concerning the quality of datasets and the effectiveness of evaluation techniques for generated summaries. In this context, we examine these limitations further with the help of three quality measures, namely, Information Coverage, Entity Hallucination, and Summarization Complexity. As a part of this work, we investigate two widely used datasets (XSUM and CNN-DM) and three existing models (BART, PEGA-SUS, and BRIO) and report our findings. Some key insights are: 1) Cumulative ROUGE score is an inappropriate evaluation measure since few high-scoring samples dominate the overall performance, 2) Existing summarization models have limited capability for information coverage and hallucinate to generate factual information, and 3) Compared to the modelgenerated summaries, the reference summaries have lowest information coverage and highest entity hallucinations reiterating the need of new and better reference summaries.