A5049441885- Natural Language Processing Techniques
- Speech and dialogue systems
- Semantic Web and Ontologies
- Topic Modeling
- Social Robot Interaction and HRI
- Multi-Agent Systems and Negotiation
- AI in Service Interactions
- Robotics and Automated Systems
- German Literature and Culture Studies
- Corporate Governance and Management
- Context-Aware Activity Recognition Systems
- semigroups and automata theory
- Advanced Database Systems and Queries
- Rough Sets and Fuzzy Logic
- Speech Recognition and Synthesis
- Syntax, Semantics, Linguistic Variation
- Algorithms and Data Compression
- Biomedical Text Mining and Ontologies
- Logic, programming, and type systems
- Flexible and Reconfigurable Manufacturing Systems
- Human-Automation Interaction and Safety
- Model-Driven Software Engineering Techniques
- Walter Benjamin Studies Compilation
- Soil Mechanics and Vehicle Dynamics
- Robotic Path Planning Algorithms
German Research Centre for Artificial Intelligence
2008-2024
Saarland University
2023
Foundation for Research and Technology Hellas
2022
University of Crete
2022
FORTH Institute of Computer Science
2022
Université franco-allemande
2011
Deutsches Forschungsnetz
1995-2005
For robots to interact effectively with human users they must be capable of coordinated, timely behavior in response social context. The Adaptive Strategies for Sustainable Long-Term Social Interaction (ALIZ-E) project focuses on the design long-term, adaptive interaction between and child real-world settings. In this paper, we report iterative approach taken scientific technical developments toward goal: advancing individual competencies integrating them form an autonomous robotic system...
For robots to interact effectively with human users they must be capable of coordinated, timely behavior in response social context. The Adaptive Strategies for Sustainable Long-Term Social Interaction (ALIZ-E) project focuses on the design long-term, adaptive interaction between and child real-world settings. In this paper, we report iterative approach taken scientific technical developments toward goal: advancing individual competencies integrating them form an autonomous robotic system...
Social robots have the potential to provide support in a number of practical domains, such as learning and behaviour change. This is particularly relevant for children, who proven receptive interactions with social robots. To reach therapeutic goals, issues need be investigated, notably design an effective child-robot interaction (cHRI) ensure child remains engaged relationship that educational goals are met. Typically, current cHRI research experiments focus on single type activity (e.g....
Social or humanoid robots do hardly show up in "the wild", aiming at pervasive human benefits such as child health. This paper presents the socio-cognitive engineering (SCE) methodology for required field research \& development of robots, focusing on incremental a social robot and child-robot activities that support daily diabetes management processes children, aged between 7 14 years (i.e., supporting healthy lifestyle). The SCE helps to integrate into human-agent/robot system: (a)...
This paper describes new and improved techniques which help a unification-based parser to process input efficiently robustly. In combination these methods result in speed-up parsing time of more than an order magnitude. The are correct the sense that none them rule out legal applications.
We present an architecture for the integration of shallow and deep NLP components which is aimed at flexible combination different language technologies a range practical current future applications. In particular, we describe high-level HPSG parsing system with high-performance components, ranging from named entity recognition to chunk clause recognition. The enrich representation natural text layers new XML meta-information using single shared data structure, called chart. details methods,...
We present an implemented compilation algorithm that translates HPSG into lexicalized feature-based TAG, relating concepts of the two theories. While has a more elaborated principle-based theory possible phrase structures, TAG provides means to represent structures explicitly. Our objectives are met by giving clear definitions determine projection from lexicon, and identify "maximal" projections, auxiliary trees foot nodes.
We present a novel, data-driven method for integrated shallow and deep parsing. Mediated by an XML-based multi-layer annotation architecture, we interleave robust, but accurate stochastic topological field parser of German with constraint-based HPSG parser. Our annotation-based dovetailing phrasal constraints is highly flexible, allowing targeted fine-grained guidance conduct systematic experiments that demonstrate substantial performance gains.
The natural language system DISCO is described. It combines• a powerful and flexible grammar development system;• linguistic competence for German including morphology, syntax semantics;• new methods performance modeling on the basis of high-level grammars;• modelling multi-agent dialogue competence;• an interesting sample application appointment scheduling calendar management.
This paper presents the results from an experiment with a conversational human-robot interaction system aimed at long-term support for diabetic children. The offers set of activities to help child improve its capability manage diabetes. There is large body literature on techniques that artificial agents can use establish and maintain social-emotional relationships their users. novel aspect in present study inclusion off-activity talk interspersed within pertaining activity hand elicit...
This video paper describes the practical outcome of first milestone a project aiming at setting up so-called Hybrid Team that can accomplish wide variety different tasks. In general, aim is to realize and examine collaboration augmented humans with autonomous robots, virtual characters SoftBots (purely software based agents) working together in common The accompanying shows customized packaging scenario be downloaded from http://hysociatea.dfki.de/?p=441.
Making the transition to long-term interaction with social-robot systems has been identified as one of main challenges in human-robot interaction. This article identifies four design principles address this challenge and applies them a real-world implementation: cloud-based robot control, modular design, common knowledge base for all applications, hybrid artificial intelligence decision making reasoning. The control architecture includes Knowledge-base (ontologies), Data-base, “Hybrid...
We describe a novel method for coping with ungrammatical input based on the use of chart-like data structures, which permit anytime processing. Priority is given to deep syntactic analysis. Should this fail, best partial analyses are selected, according shortest-paths algorithm, and assembled in robust processing phase. The has been applied speech translation project large HPSG grammars.
We describe an implemented hybrid reasoning architecture that is used in EU-funded project called MUSING (www.musing.eu) which dedicated towards the investigation of semantic-based business intelligence solutions. The platform builds on publicly available software, such as Pellet, OWLIM, Jena, and Sesame. uses extends existing OWL ontologies (e.g., PROTON) assumes rule-based to take place top OWL. pros cons each subsystem w.r.t. needs we have encountered during our investigation. explain...