The world of services on the Web, thus far limited to "classical" Web services based on WSDL and SOAP, has been increasingly marked by the domination of Web APIs, characterised by their relative simplicity and their natural suitability for the Web. Currently, the development of Web APIs is rather autonomous, guided by no established standards or rules, and Web API documentation is commonly not based on an interface description language such as WSDL, but is rather given directly in HTML as part of a webpage. As a result, the use of Web APIs requires extensive manual effort and the wealth of existing work on supporting common service tasks, including discovery, composition and invocation, can hardly be reused or adapted to APIs. Before we can achieve a higher level of automation and can make any significant improvement to current practices and technologies, we need to reach a deeper understanding of these. Therefore, in this paper we present a thorough analysis of the current landscape of Web API forms and descriptions, which has up-to-date remained unexplored. We base our findings on manually examining a body of publicly available APIs and, as a result, provide conclusions about common description forms, output types, usage of API parameters, invocation support, level of reusability, API granularity and authentication details. The collected data provides a solid basis for identifying deficiencies and realising how we can overcome existing limitations. More importantly, our analysis can be used as a basis for devising common standards and guidelines for Web API development.

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.

No abstract

The ongoing digital transformation has the potential to revolutionize nearly all industrial manufacturing processes. However, its concrete requirements and implications are still not sufficiently investigated. In order to establish a common understanding, a multitude of initiatives have published guidelines, reference frameworks and specifications, all intending to promote their particular interpretation of the Industrial Internet of Things (IIoT). As a result of the inconsistent use of terminology, heterogeneous structures and proposed processes, an opaque landscape has been created. The consequence is that both new users and experienced experts can hardly manage to get an overview of the amount of information and publications, and make decisions on what is best to use and to adopt. This work contributes to the state of the art by providing a structured analysis of existing reference frameworks, their classifications and the concerns they target. We supply alignments of shared concepts, identify gaps and give a structured mapping of regarded concerns at each part of the respective reference architectures. Furthermore, the linking of relevant industry standards and technologies to the architectures allows a more effective search for specifications and guidelines and supports the direct technology adoption.

The concept of blockchain technology has gained significant momentum in practice and research in the past few years, as it provides an effective way for addressing the issues of anonymity and traceability in distributed scenarios with multiple parties, which have to exchange information and want to securely collaborate with each other. However, up-to-date, the impact of the structure and setup of business networks on successfully applying blockchain technology, remains largely unexplored.We propose a model-driven approach, combining an ontology and a layer model, that is capable of capturing the properties of existing blockchain-driven business networks. The layers are used to facilitate the comprehensive description of such networks. We also introduce the Blockchain Business Network Ontology (BBO), formalizing the concepts and properties for describing the integral parts of a blockchain network. We show the practical applicability of our work by evaluating and applying it to an available blockchain use case.

The proposed concept paves the way for holistic treatment strategy planning by enabling joint storing and processing of heterogeneous data from various information sources.

The disruptive potential of the upcoming digital transformations for the industrial manufacturing domain have led to several reference frameworks and numerous standardization approaches. On the other hand, the Semantic Web community has made significant contributions in the field, for instance on data and service description, integration of heterogeneous sources and devices, and AI techniques in distributed systems. These two streams of work are, however, mostly unrelated and only briefly regard each others requirements, practices and terminology. We contribute to closing this gap by providing the Semantic Asset Administration Shell, an RDF-based representation of the Industrie 4.0 Component. We provide an ontology for the latest data model specification, created a RML mapping, supply resources to validate the RDF entities and introduce basic reasoning on the Asset Administration Shell data model. Furthermore, we discuss the different assumptions and presentation patterns, and analyze the implications of a semantic representation on the original data. We evaluate the thereby created overheads, and conclude that the semantic lifting is manageable, also for restricted or embedded devices, and therefore meets the needs of Industrie 4.0 scenarios.

Adaptive service selection is acknowledged to provide a certain number of advantages to optimize the service provisioning process or to cater for advanced service brokering. Semantic Web Services, that is services that have been enriched with semantic annotations have often been used for providing adaptive service selection by deferring the binding of services until runtime. Thus far, however, research on Semantic Web Services has mainly been dominated by rich conceptual frameworks such as WSMO and OWL-S which require a significant effort towards the annotation of services and rely on complex reasoning for which there are no efficient solutions that can scale to the Web yet. In this chapter, inline with current trends on the Semantic Web that sacrifice expressivity in favour of performance, we present a novel approach to providing adaptive service selection that relies on simple conceptual models for services and less expressive formalisms for which there currently exist mature and performant implementations. In particular, we present a set of concep-