A5088730772- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Natural Language Processing Techniques
- Topic Modeling
- Model-Driven Software Engineering Techniques
- Advanced Text Analysis Techniques
- Advanced Software Engineering Methodologies
- Business Process Modeling and Analysis
- Teaching and Learning Programming
- Experimental Learning in Engineering
- Simulation Techniques and Applications
- Software Engineering Techniques and Practices
- Digital Marketing and Social Media
- linguistics and terminology studies
- Educational Leadership and Innovation
- Advanced Database Systems and Queries
- Complex Network Analysis Techniques
- Data Visualization and Analytics
- Family Business Performance and Succession
- Service-Oriented Architecture and Web Services
- Software Engineering Research
- Higher Education Learning Practices
- Online and Blended Learning
- Education Methods and Technologies
- Technology-Enhanced Education Studies
Bielefeld University
2018-2022
Westsächsische Hochschule Zwickau
2016-2020
Abstract Background The evidence-based medicine paradigm requires the ability to aggregate and compare outcomes of interventions across different trials. This can be facilitated partially automatized by information extraction systems. In order support development systems that extract from published clinical trials at a fine-grained comprehensive level populate knowledge base, we present richly annotated corpus two levels. At first level, entities describe components PICO elements (e.g.,...
Evidence-based medicine propagates that medical/clinical decisions are made by taking into account high-quality evidence, most notably in the form of randomized clinical trials. decision-making requires aggregating evidence available multiple trials to reach -by means systematic reviews- a conclusive recommendation on which treatment is best suited for given patient population. However, it challenging produce reviews keep up with ever-growing number published Therefore, new computational...
Supervised machine learning algorithms require training data whose generation for complex relation extraction tasks tends to be difficult. Being optimized at sentence level, many annotation tools lack in facilitating the of relational structures that are widely spread across text. This leads non-intuitive and cumbersome visualizations, making process unnecessarily time-consuming. We propose SANTO, an easy-to-use, domain-adaptive tool specialized slot filling which may involve problems...
Recent question answering and machine reading benchmarks frequently reduce the task to one of pinpointing spans within a certain text passage that answers given question. Typically, these systems are not required actually understand on deeper level allows for more complex reasoning information contained. We introduce new dataset called BiQuAD requires comprehension in order answer questions both extractive deductive fashion. The consist 4,190 closed-domain texts total 99,149 question-answer...
Modern businesses are often perceived through the lens of media. We investigate how family covered and what dimensions influence reporting. applied a text mining approach to examine media coverage its on corporate reputation firms. Pairing computational-algorithms with research domain business generate novel insights in build concept firms content output is. Furthermore, we measured effect topics articles mentioned. find empirical support for five which particularly relevant influence:...