Aspect-based summarization differs from generic text-summarization in which the generated summary must be conditioned on a given topic. A fundamental challenge to the aspect-based summarization approach is the lack of labeled data for training models, which limits the usage of supervised methods. One approach to address this issue is to introduce human intervention to generate unique datasets per aspect. However, there is a large number of possible aspects to summarize which makes this option impossible to scale. This limits the use of typical modeling techniques, and requires methods which excel in few-shot, or ideally zero-shot regimes. Hence, in this research, we propose a modular, two-step approach that does not need any aspect-based supervision. This research combines recent advances in zero-shot text classification and generic summarization in a novel way. The backbone of the proposed approach is a transformer network trained for the task of textual entailment, which is used to reduce a document to the set of on topic sentences. In the experiments, our model achieves a new state of the art compared to other unsupervised models on the MA-News dataset (ROUGE-1 35.70 and ROUGE-2 15.52), and even outperforms fine-tuned models without any supervision of its own.

OBJECTIVE: This study seeks to develop a fully automated method of generating synthetic data from a real dataset that could be employed by medical organizations to distribute health data to researchers, reducing the need for access to real data. We hypothesize the application of Bayesian networks will improve upon the predominant existing method, medBGAN, in handling the complexity and dimensionality of healthcare data. MATERIALS AND METHODS: We employed Bayesian networks to learn probabilistic graphical structures and simulated synthetic patient records from the learned structure. We used the University of California Irvine (UCI) heart disease and diabetes datasets as well as the MIMIC-III diagnoses database. We evaluated our method through statistical tests, machine learning tasks, preservation of rare events, disclosure risk, and the ability of a machine learning classifier to discriminate between the real and synthetic data. RESULTS: Our Bayesian network model outperformed or equaled medBGAN in all key metrics. Notable improvement was achieved in capturing rare variables and preserving association rules. DISCUSSION: Bayesian networks generated data sufficiently similar to the original data with minimal risk of disclosure, while offering additional transparency, computational efficiency, and capacity to handle more data types in comparison to existing methods. We hope this method will allow healthcare organizations to efficiently disseminate synthetic health data to researchers, enabling them to generate hypotheses and develop analytical tools. CONCLUSION: We conclude the application of Bayesian networks is a promising option for generating realistic synthetic health data that preserves the features of the original data without compromising data privacy.

In order to improve the level of decision making and competitive advantage, organizations try to learn and develop new knowledge management techniques that are suited for the evolving global economy. Decision makers are becoming increasingly faced with a dilemma: great difficulty arises in sharing knowledge where distributed and heterogeneous data sources are so rich in terms of their information content. In order to address the problem of knowledge sharing, this article proposes a common knowledge sharing model— the 24-hour knowledge factory—of grid computing founded on case-based reasoning (CBR). This article begins with a description of the 24-hour knowledge factory, the enterprise common knowledge shared (ECKS) methodology and the time-shift sharing model. Next, the notion of a CBR-adapted approach for 24-hour knowledge factory, based on grid computing, is presented. Third, based on the ECKS concept, this article analyzes the use of the model described in this article in decision evolution and builds upon enterprise sharing structure ECK modeling, focusing on activity-work sharing, passive-work sharing and mix-work sharing. Multiple types of enterprise common knowledge transfer mechanisms are presented in this article.

editorial Free Access Share on Guest editorial: The Internet and outsourcing Authors: Amar Gupta University of Arizona University of ArizonaView Profile , Satwiksai Seshasai IBM and MIT IBM and MITView Profile Authors Info & Claims ACM Transactions on Internet TechnologyVolume 7Issue 3August 2007 pp 13–eshttps://doi.org/10.1145/1275505.1275506Published:01 August 2007Publication History 0citation512DownloadsMetricsTotal Citations0Total Downloads512Last 12 Months13Last 6 weeks2 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

Several of the outsourcing endeavors of today will gradually converge to a hybrid outsourcing model that will involve a team spread across three or more strategically-located centers interconnected by Internet technology. White-collar professionals in the US, Australia, and Poland, for example, could each work on a standard 9--5 basis, transfer the activity to a colleague in the next center, thereby enabling work to be performed on a round-the-clock basis. The effective use of sequential workers in such a 24-hour knowledge factory requires that professional tasks be broken down to the level where individuals can work on them with minimal interaction with their peers, and where new approaches can be employed to reduce the effort involved in transitioning from one employee to the next. This article describes an Internet-based prototype system that uses a Web-based interactive approach, coupled with a unique data model, to optimize collection and storage of design rationale and history from stakeholders and workers. The idea of multiple individuals acting as one “composite persona” is explored in the context of facilitating tasks and knowledge to be shared across the Internet in a seamless manner. The article also describes related activities in the commercial arena.

Third-party architectures for data publishing over the Internet today are receiving growing attention, due to their scalability properties and to the ability of efficiently managing large number of subjects and great amount of data. In a third-party architecture, there is a distinction between the Owner and the Publisher of information. The Owner is the producer of information, whereas Publishers are responsible for managing (a portion of) the Owner information and for answering subject queries. A relevant issue in this architecture is how the Owner can ensure a secure and selective publishing of its data, even if the data are managed by a third-party, which can prune some of the nodes of the original document on the basis of subject queries and access control policies. An approach can be that of requiring the Publisher to be trusted with regard to the considered security properties. However, the serious drawback of this solution is that large Web-based systems cannot be easily verified to be secure and can be easily penetrated. For these reasons, we propose an alternative approach, based on the use of digital signature techniques, which does not require the Publisher to be trusted. The security properties we consider are authenticity and completeness of a query response, where completeness is intended with regard to the access control policies stated by the information Owner. In particular, we show that, by embedding in the query response one digital signature generated by the Owner and some hash values, a subject is able to locally verify the authenticity of a query response. Moreover, we present an approach that, for a wide range of queries, allows a subject to verify the completeness of query results.

1 Introduction and motivation One may claim that the exponential growth in the amount of data provides great opportunities for data mining. Reality can be different though. In many real world applications, the number of sources over which this information is fragmented grows at an even faster rate, resulting in barriers to widespread application of data mining and missed business opportunities. Let us illustrate this paradox with a motivating example from database marketing.

In this article we present a distributed system that stores name-to-address bindings and provides name resolution to a network of computers. This name system consists of a network of name services that are individually self-configuring and self-administering. The name service consists of an agent program that works in conjunction with the current implementation of the Domain Name System (DNS) program. The DNS agent program automatically configures the Berkeley Internet Name Domain (BIND) process during start-up and dynamically reconfigures and administers the BIND process based on the changing state of the network. The proposed name system offers high scalability and fault-tolerance capabilities and communicates using standard Internet protocols.

As part of their strategy for incorporating electronic commerce capabilities, many organizations are involved in the development of information systems that will establish effective linkages with their suppliers, customers, and other channel partners involved in transportation, distribution, warehousing and maintenance activities.These linkages have given birth to comprehensive data warehouses that integrate operational data with supplier, customer, channel partners and market information.Data mining techniques can now provide the technological leap needed to structure and prioritize information from these data warehouses to address specific end-user problems.Emerging data mining techniques permit the semi-automatic discovery of patterns, associations, changes, anomalies, rules, and statistically significant structures and events in data.Very significant business benefits have been attained through the integration of data mining techniques with current information systems aiding electronic commerce.This paper explains key data mining principles that can play a pivotal role in an electronic commerce environment.The paper also highlights two case studies in which neural network-based data mining techniques were used for inventory optimization.The results from the data mining prototype in a large medical distribution company provided the rationale for the strategy to reduce the total level of inventory by 50% (from a billion dollars to half a billion dollars) in the particular organization, while maintaining the same level of probability that a particular customer's demand will be satisfied.The second case study highlights the use of neural network based data mining techniques for forecasting hot metal temperatures in a steel mill blast furnace.

This paper discusses a technique for locating the courtesy amount block on bank checks. In the analysis and recognition process, connected components in the image are identified first. Then, strings are constructed on the basis of proximity and horizontal alignment of characters. Next, a set of rules and heuristics are applied to these strings to choose the correct one. The chosen string is only accepted if it passes a verification test, which includes an attempt to recognize the currency sign. A deterministic finite automaton system is then used for segmenting the handprinted courtesy amount. Finally, the separated components are passed on to a neural network based recognition system.

The topology and the capacity of a traditional multilayer neural system, as measured by the number of connections in the network, has surprisingly little impact on its generalization ability. This paper presents a new adaptive modular network that offers superior generalization capability. The new network provides significant fault tolerance, quick adaption to novel inputs, and high recognition accuracy. We demonstrate this paradigm on recognition of unconstrained handwritten characters.

The transformation of existing local databases to meet diverse application needs at the global level is performed through a four-layered procedure that stresses total schema integration and virtual integration of local databases. The proposed methodology covers both schema integration and database integration, and uses a four-layered schema architecture (local schemata, local object schemata, global schema, and global view schemata) with each layer presenting an integrated view of the concepts that characterize the layer below. Mechanisms for accomplishing this objective are presented in theoretical terms, along with a running example. Object equivalence classes, property equivalence classes, and other related concepts are discussed in the context of logical integration of heterogeneous schemata, while object instance equivalence classes and property instance equivalence classes, and other related concepts are discussed for data integration purposes. The proposed methodology resolves naming conflicts, scaling conflicts, type conflicts, and level of abstraction, and other types of conflicts during schema integration, and data inconsistencies during data integration.>

A multi-staged system for off-line handwritten numeral recognition is presented here. After scanning, the digitized binary bitmap image of the source document is passed through a preprocessing stage which performs segmentation, thinning and rethickening, normalization, and slant correction. The recognizer is a three-layered neural net trained with back-propagation algorithm. While a few systems that use three-layered nets for recognition have been presented in the literature, the contribution of our system is based on two aspects: elaborate preprocessing based on structural pattern recognition methods combined with a neural net based recognizer; and integration of neural net based and structural pattern recognition methods to produce high accuracies.

A number of image processing and pattern recognition applications demand that a raw digitized binary pattern array be normalized, so that the constituent components of that array are of uniform thickness. The thinning process reduces such components to a thickness of one pixel, or sometimes a few pixels. This paper describes a strategy for farther enhancing the operational speed of one of the fastest parallel algorithms proposed in the literature.>

This paper examines several line-drawing pattern recognition methods for handwritten character recognition. They are the picture descriptive language (PDL), Berthod and Maroy (BM), extended Freeman's chain code (EFC), error transformation (ET), tree grammar (TG), and array grammar (AG) methods. A new character recognition scheme that uses improved extended octal codes as primitives is introduced. This scheme offers the advantages of handling flexible sizes, orientations, and variations, the need for fewer learning samples, and lower degree of ambiguity. Finally, the simulation of off-line character recognition by the real-time on-line counterpart is investigated.