A5002210292- Topic Modeling
- Privacy-Preserving Technologies in Data
- Privacy, Security, and Data Protection
- Web Data Mining and Analysis
- Natural Language Processing Techniques
- Cybercrime and Law Enforcement Studies
- Digital Rights Management and Security
- Text and Document Classification Technologies
- Wikis in Education and Collaboration
- Algorithms and Data Compression
- Multi-Agent Systems and Negotiation
- Text Readability and Simplification
- Internet Traffic Analysis and Secure E-voting
- Semantic Web and Ontologies
- Business Process Modeling and Analysis
Fraunhofer Institute for Intelligent Analysis and Information Systems
2020-2024
University of Bonn
2016-2020
With the omnipresent availability and use of cloud services, software tools, Web portals or legal contracts in form End-User License Agreements (EULA) regulating their are paramount importance. Often textual documents describing these regulations comprise many pages can not be reasonably assumed to read understood by humans. In this work, we describe a method for extracting clustering relevant parts such documents, including permissions, obligations, prohibitions. The is based on semantic...
Ignoring End-User License Agreements (EULAs) for online services due to their length and complexity is a risk undertaken by the majority of mobile service users. This paper presents an Ontology-Based Information Extraction (OBIE) method EULA term phrase extraction facilitate better understanding humans. An ontology capturing important terms relationships has been developed used guide OBIE process. Through feedback cycle we have improved its domain-specific coverage identifying additional...
Managing complex AI systems requires insight into a model's decision-making processes. Understanding how these arrive at their conclusions is essential for ensuring reliability. In the field of explainable natural language processing, many approaches have been developed and evaluated. However, experimental analysis explainability text classification has largely constrained to short binary classification. this applied work, we study real-world task where goal assess technological suitability...