A5000758128- Semantic Web and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Multimodal Machine Learning Applications
- Advanced Graph Neural Networks
- Biomedical Text Mining and Ontologies
- Domain Adaptation and Few-Shot Learning
- Web Data Mining and Analysis
- Data Quality and Management
- Data Management and Algorithms
- Scientific Computing and Data Management
- Advanced Text Analysis Techniques
- Recommender Systems and Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Database Systems and Queries
- Bayesian Modeling and Causal Inference
- Data Stream Mining Techniques
- Advanced Neural Network Applications
- Speech and dialogue systems
- Image Retrieval and Classification Techniques
- Business Process Modeling and Analysis
- Logic, Reasoning, and Knowledge
- Complex Network Analysis Techniques
- Distributed and Parallel Computing Systems
- Visual Attention and Saliency Detection
Universität Trier
2019-2025
FZI Research Center for Information Technology
2023
Literaturarchiv
2020
Centre for Digital Humanities
2020
Behörde für Gesundheit und Verbraucherschutz
2020
Karlsruhe Institute of Technology
2010-2019
Iberia (Spain)
2017
Technical University of Munich
2006-2010
University of Koblenz and Landau
2005-2008
In recent years, several noteworthy large, cross-domain, and openly available knowledge graphs (KGs) have been created. These include DBpedia, Freebase, OpenCyc, Wikidata, YAGO. Although extensively in use, these KGs not subject to an in-depth comparison so far. this survey, we pro vide data quality criteria according which can be analyzed analyze compare the above mentioned KGs. Furthermore, propose a framework for finding most suitable KG given setting.
In many languages, sparse availability of resources causes numerous challenges for textual analysis tasks.Text classification is one such standard tasks that hindered due to limited label information in lowresource languages.Transferring knowledge (i.e.label information) from high-resource low-resource languages might improve text as compared the other approaches like machine translation.We introduce BRAVE (Bilingual paRAgraph VEctors), a model learn bilingual distributed representations...
A combined approach of deductive and inductive reasoning can leverage the clear separation between evolving (streaming) static parts online knowledge at conceptual technological levels. What are hottest topics discussed on Twitter? Which have my close friends in last hour? movie is friend most likely to watch next? Tuscan red wine should I recommend? With many popular social networks publishing microblogs feeds, information required answer these queries becoming available Web.
The information perceived via visual observations of real-world phenomena is unstructured and complex. Computer vision (CV) the field research that attempts to make use information. Recent approaches CV utilize deep learning (DL) methods as they perform quite well if training testing domains follow same underlying data distribution. However, it has been shown minor variations in images occur when these are used real world can lead unpredictable catastrophic errors. Transfer area machine...
Collaborative tagging systems with user generated content have become a fundamental element of websites such as Delicious, Flickr or CiteULike. By sharing common knowledge, massively linked semantic data sets are that provide new challenges for mining. In this paper, we reduce the complexity in these by finding meaningful topics serve to group similar users and recommend tags resources users. We propose well-founded probabilistic approach can model every aspect collaborative system....
The ever-increasing quantities of structured knowledge on the Web and impending need multilinguality cross-linguality for information access pose new challenges but at same time open up opportunities extraction research. In this regard, cross-lingual semantic annotation has emerged as a topic major interest it is essential to build tools that can link words phrases in unstructured text one language resources bases any other language. paper, we demonstrate X-LiSA, an infrastructure...
The proximity between newspapers and political parties is strongly subjective difficult to measure. Yet, tendencies of can have a significant impact on voters’ opinion‐forming ought be known by the public in transparent timely manner. This article introduces Sentiment Political Compass ( SPC ), data‐driven framework for analyzing bias toward parties. Using SPC, are embedded two‐dimensional space (left‐leaning vs. right‐leaning, libertarian autocratic). To assess informative value our...
Increasingly, data is published in the form of semantic graphs. The most notable example Linked Open Data (LOD) initiative where an increasing number sources are Semantic Web's Resource Description Framework and