About
12
Publications
1,561
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
63
Citations
Publications
Publications (12)
Retrieval-augmented generation has become an effective mechanism for conversational systems in domain-specific settings. Retrieval of a wrong document due to the lack of context from the user utterance may lead to wrong answer generation. Such an issue may reduce the user engagement and thereby the system reliability. In this paper, we propose a co...
For rupture risk assessment of intracranial aneurysms, 3D surface model extraction might be time-consuming but supports calculation of morphological and hemodynamical parameters. We present a geometric deep learning approach to segment the intracranial vascular domain of interest in 3D surface meshes comprising only the aneurysm and surrounding ves...
It is a long-standing desire of industry and research to automate the software development and testing process as much as possible. Model-based design and testing methods have been developed to automate several process steps and handle the growing complexity and variability of software systems. However, major effort is still required to create spec...
Die Grundlage für einen effizienten Softwareentwicklungs-und Testprozess ist die Spezifikation von Anforderungen, die die Funktionalität und Qualitätseigenschaften des zu entwickelnden Softwareprodukts beschreiben soll. Anforderungsspezifikationen sind zumeist in natürlicher Sprache formuliert, was die Kommunikation zwischen den unterschiedlichen B...
Assuring the quality of complex and highly configurable software systems is a demanding and time-consuming process. Especially for safety-critical systems, extensive testing based on requirements is necessary. Methods for model-based test automation in agile software development offer the possibility to overcome these difficulties. However, it is s...
Textual entailment classification is one of the hardest tasks for the Natural Language Processing community. In particular, working on entailment with legal statutes comes with an increased difficulty, for example in terms of different abstraction levels, terminology and required domain knowledge to solve this task. In course of the COLIEE competit...
A large amount of present green light optimal speed advisory (GLOSA) systems are for private vehicles. However, as one of nonnegligible transportation modes, public transportation is worth more attention. Some GLOSAs just provide several driving models with fixed speeds and accelerations which is extremely difficult for human-drivers to obey strict...
Due to the growing complexity and rapid changes of software systems, the assurance of their quality becomes increasingly difficult. Model-based testing in agile development is a way to overcome these difficulties. However, major effort is still required to create specification models from a large set of functional requirements provided in natural l...