arXiv subjects

Maria Maleshkova

Publications and source records attributed to Maria Maleshkova.

25 records · Page 2Linked to original sources

arXiv2020

MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities

In this paper, we introduce the MLM (Multiple Languages and Modalities) dataset - a new resource to train and evaluate multitask systems on samples in multiple modalities and three languages. The generation process and inclusion of semantic data provide a resource that further tests the ability for multitask systems to learn relationships between entities. The dataset is designed for researchers and developers who build applications that perform multiple tasks on data encountered on the web and in digital archives. A second version of MLM provides a geo-representative subset of the data with weighted samples for countries of the European Union. We demonstrate the value of the resource in developing novel applications in the digital humanities with a motivating use case and specify a benchmark set of tasks to retrieve modalities and locate entities in the dataset. Evaluation of baseline multitask and single task systems on the full and geo-representative versions of MLM demonstrate the challenges of generalising on diverse data. In addition to the digital humanities, we expect the resource to contribute to research in multimodal representation learning, location estimation, and scene understanding.

cs.LG↗

arXiv2020

Training Multimodal Systems for Classification with Multiple Objectives

We learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple modalities creates the potential to learn rich representations of the world - but current multimodal systems only deliver marginal improvements on unimodal approaches. Neural networks learn sampling noise during training with the result that performance on unseen data is degraded. This research introduces a second objective over the multimodal fusion process learned with variational inference. Regularisation methods are implemented in the inner training loop to control variance and the modular structure stabilises performance as additional neurons are added to layers. This framework is evaluated on a multilabel classification task with textual and visual inputs to demonstrate the potential for multiple objectives and probabilistic methods to lower variance and improve generalisation.

cs.LG↗

arXiv2019

The Semantic Asset Administration Shell

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.

cs.AI↗

arXiv2019

Virtual Representations for Iterative IoT Deployment

A central vision of the Internet of Things is the representation of the physical world in a consistent virtual environment. Especially in the context of smart factories the connection of the different, heterogeneous production modules through a digital shop floor promises faster conversion rates, data-driven maintenance or automated machine configurations for use cases, which have not been known at design time. Nevertheless, these scenarios demand IoT representations of all participating machines and components, which requires high installation efforts and hardware adjustments. We propose an incremental process for bringing the shop floor closer to the IoT vision. Currently the majority of systems, components or parts are not yet connected with the internet and might not even provide the possibility to be technically equipped with sensors. However, those could be essential parts for a realistic digital shop floor representation. We, therefore, propose Virtual Representations, which are capable of independently calculating a physical object's condition by dynamically collecting and interpreting already available data through RESTful Web APIs. The internal logic of such Virtual Representations are further adjustable at runtime, since changes to its respective physical object, its environment or updates to the resource itself should not cause any downtime.

cs.SE↗

arXiv2019

RESTful or RESTless -- Current State of Today's Top Web APIs

Recent developments in the world of services on the Web show that both the number of available Web APIs as well as the applications built on top is constantly increasing. This trend is commonly attributed to the wide adoption of the REST architectural principles. Still, the development of Web APIs is rather autonomous and it is up to the providers to decide how to implement, expose and describe the Web APIs. The individual implementations are then commonly documented in textual form as part of a webpage, showing a wide variety in terms of content, structure and level of detail. As a result, client application developers are forced to manually process and interpret the documentation. 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 their similarities and differences. Therefore, in this paper we present a thorough analysis of the most popular Web APIs through the examination of their documentation. We 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 builds a solid foundation for identifying deficiencies and can be used as a basis for devising common standards and guidelines for Web API development.

cs.SE↗

arXiv2019

Smart Web Services (SmartWS) -- The Future of Services on the Web

The past few years have been marked by an increased use of sensor technologies, abundant availability of mobile devices, and growing popularity of wearables, which enable the direct integration of their data as part of rich client applications. Despite the potential and added value that such aggregate applications bring, the implementations are usually custom solutions for particular use cases and do not support easy integration of further devices. To this end, the vision of the Web of Things (WoT) is to leverage Web standards in order to interconnect all types of devices and real-world objects, and thus to make them a part of the World Wide Web (WWW) and provide overall interoperability. In this context we introduce Smart Web Services (SmartWS) that not only provide remote access to resources and functionalities, by relying on standard communication protocols, but also encapsulate `intelligence'. Smartness features can include, for instance, context-based adaptation, cognition, inference and rules that implement autonomous decision logic in order to realize services that automatically perform tasks on behalf of the users, without requiring their explicit involvement. In this paper, we present the key characteristics of SmartWS, and introduce a reference implementation framework. Furthermore, we describe a specific use case for implementing SmartWS in the medical domain and specify a maturity model for determining the quality and usability of SmartWS.

cs.CY↗

arXiv2017

What does it all mean? Capturing Semantics of Surgical Data and Algorithms with Ontologies

Every year approximately 234 million major surgeries are performed, leading to plentiful, highly diverse data. This is accompanied by a matching number of novel algorithms for the surgical domain. To garner all benefits of surgical data science it is necessary to have an unambiguous, shared understanding of algorithms and data. This includes inputs and outputs of algorithms and thus their function, but also the semantic content, i.e. meaning of data such as patient parameters. We therefore propose the establishment of a new ontology for data and algorithms in surgical data science. Such an ontology can be used to provide common data sets for the community, encouraging sharing of knowledge and comparison of algorithms on common data. We hold that this is a necessary foundation towards new methods for applications such as semantic-based content retrieval and similarity measures and that it is overall vital for the future of surgical data science.

cs.CY↗