A5082238675- Semantic Web and Ontologies
- Topic Modeling
- Data Quality and Management
- Advanced Graph Neural Networks
- Natural Language Processing Techniques
- Video Analysis and Summarization
- Image Retrieval and Classification Techniques
- Digital Innovation in Industries
- Biomedical Text Mining and Ontologies
- Advanced Image and Video Retrieval Techniques
- Scientific Computing and Data Management
- Service-Oriented Architecture and Web Services
- Advanced Database Systems and Queries
- Web Data Mining and Analysis
- Text and Document Classification Technologies
- Advanced Text Analysis Techniques
- IPv6, Mobility, Handover, Networks, Security
- Library Science and Information Systems
- Music and Audio Processing
- Graph Theory and Algorithms
- Wikis in Education and Collaboration
- Digitalization, Law, and Regulation
- Mobile Agent-Based Network Management
- Machine Learning in Materials Science
- Research Data Management Practices
FIZ Karlsruhe – Leibniz Institute for Information Infrastructure
2016-2025
Karlsruhe Institute of Technology
2017-2023
Institut für Automatisierung und Informatik
2021
Leibniz Association
2017-2021
Hasso Plattner Institute
2007-2016
University of Potsdam
2007-2016
Software (Germany)
2011
Friedrich Schiller University Jena
2002-2007
Universität Trier
1998-2002
Ross School
1966
We present GERBIL, an evaluation framework for semantic entity annotation. The rationale behind our is to provide developers, end users and researchers with easy-to-use interfaces that allow the agile, fine-grained uniform of annotation tools on multiple datasets. By these means, we aim ensure both tool developers can derive meaningful insights pertaining extension, integration use applications. In particular, GERBIL provides comparable results so as them easily discover strengths weaknesses...
Knowledge representation in the Materials Science and Engineering (MSE) domain is a vast multi-faceted challenge: Overlap, ambiguity, inconsistency terminology are common. Invariant (consistent) variant (context-specific) knowledge difficult to align cross-domain. Generic top-level semantic often too abstract, while MSE specific. In this paper, an approach how maintain comprehensive MSE-centric composing mid-level ontology–the Platform MaterialDigital Core Ontology (PMDco)–via...
In recent years the Web of Data experiences an extraordinary development: increasing amount Linked is available on World Wide (WWW) and new use cases are emerging continually. However, provided data only valuable if it accurate without contradictions. One essential part DBpedia, which covers structured Wikipedia. Due to its automatic extraction based Wikipedia resources that have been created by various contributors, DBpedia often error-prone. order enable detection inconsistencies this work...
Knowledge Graphs (KGs) are composed of structured information about a particular domain in the form entities and relations. In addition to KGs help facilitating interconnectivity interoperability between different resources represented Linked Data Cloud. have been used variety applications such as entity linking, question answering, recommender systems, etc. However, KG suffer from high computational storage costs. Hence, there arises necessity for representation able map dimensional into...
The local prediction of fatigue damage within polycrystals in a high-cycle setting is long-lasting and challenging task. It requires identifying grains tending to accumulate plastic deformation under cyclic loading. We address this task by transcribing ferritic steel microtexture maps from experiments into microstructure graph. Here, constitute graph nodes connected edges whenever share common boundary. Fatigue loading causes some develop slip markings, which can evolve microcracks lead...
Abstract Purpose – Linking Open Data (LOD) provides a vast amount of well structured semantic information, but many inconsistencies may occur, especially if the data are generated with help automated methods. cleansing approaches enable detection and overhauling affected sets, they difficult to apply automatically. The purpose this paper is present WhoKnows?, an online quiz that generates different kinds questionnaires from DBpedia sets. Design/methodology/approach Besides its playfulness,...
During the last years, digital lecture libraries and video portals have become more popular. However, finding efficient methods for indexing multimedia still remains a challenging task. Since text displayed in is closely related to content, it provides valuable source retrieving contents. In this paper, we present an approach automatic based on OCR technology. We developed novel segmenter automated slide structure analysis weighted DCT (discrete cosines transformation) detector. A dynamic...
Deep Convolutional Neural Networks (CNN) have recently been shown to outperform previous state of the art approaches for image classification. Their success must in parts be attributed availability large labeled training sets such as provided by ImageNet benchmarking initiative. When data is scarce, however, CNNs proven fail learn descriptive features. Recent research shows that supervised pre-training on external followed domain-specific fine-tuning yields a significant performance boost...
Today, increasing numbers of people are interacting online and a lot textual comments being produced due to the explosion communication. However, paramount inconvenience within environments is that shared digital platforms can hide hazards, such as fake news, insults, harassment, and, more in general, may hurt someone’s feelings. In this scenario, detection kind toxicity has an important role moderate Deep learning technologies have recently delivered impressive performance Natural Language...
Abstract Scholarly data is growing continuously containing information about the articles from a plethora of venues including conferences, journals, etc. Many initiatives have been taken to make scholarly available in form Knowledge Graphs (KGs). These efforts standardize these and them accessible also led many challenges such as exploration articles, ambiguous authors, This study more specifically targets problem Author Name Disambiguation (AND) on KGs presents novel framework, Literally...
Recent rises in political polarization across the globe are often ascribed to algorithmic content filtering on social media, news platforms, or search engines. The widespread usage of recommendation systems (NRS) is theorized drive users homogenous information environments and, thereby, affective, ideological, and perceived polarization. To test this assumption, we conducted an online experiment ( n = 750) with running algorithms that enriches content-based NRS negative neutral sentiment....
The International Semantic Web Research School (ISWS) is a week-long intensive program designed to immerse participants in the field. This document reports collaborative effort performed by ten teams of students, each guided senior researcher as their mentor, attending ISWS 2023. Each team provided different perspective topic creative AI, substantiated set research questions main subject investigation. 2023 edition focuses on intersection technologies and Creative AI. explored various...
The text displayed in a lecture video is closely related to the content. Therefore, it provides valuable source for indexing and retrieving contents. Textual content can be detected, extracted analyzed automatically by OCR (Optical Character Recognition) techniques. In this paper, we present an approach automated based on technology: Firstly, developed novel segmenter slide structure analysis. Having adopted localization verification scheme, perform detection secondly. We employ SWT (stroke...