TOPIC 1: Applications of current NLP Technologies in Requirements Engineering
Introduction: Requirements Engineering consists of multiple activities and techniques in order to define, document and maintain software artefacts. Especially the initial phase of Requirements Elicitation plays a vital role for the success of a software project, which involves different practices (often interviews and questionnaires based on natural language) to discover and gather requirements from the relevant stakeholders. Advances in Natural Language Processing (NLP) in recent years have also impacted Requirements Engineering. The goal of this seminar work is to provide a clear overview of approaches that apply various NLP technologies to support Requirements Elicitation with a focus on current approaches (e.g. state-of-the-art language models).
Goal and Objective: Overview of different state-of-the-art approaches that apply current NLP technologies in the field of Requirements Engineering and comparison between them.
Introduction: Currently, the explainability of AI techniques (XAI) is a widely discussed topic, both in AI research and in society. Missing or insufficient explanatory capabilities of AI-based systems are a serious limitation for the use of these techniques in many applications domains for various reasons.
Goal and Objective: In this seminar you will familiarize yourself with XAI approaches for AI techniques (like artificial neural networks) based on scientific literature as well as your own exploration.
TOPIC 3: Micro-Service Composition for Open Software Systems
Introduction: Currently, more and more Application Programming Interfaces (API) are accessible using e.g. internet protocols. For example, API search engines such as RAPID API or Programmable Web allow humans to quickly find and interpret use case relevant services. However, such an interpretation is a complex problems for software systems (e.g. IoT devices or intelligent service systems ) as input parameter names or response messages are just character sequenecs. If a software platform is not hard-coded towards accessing predefined external APIs, then matching and mapping approaches can be utilized for determining required services at runtime. This can potentially boost up the amount of use cases a service system can handle with only minimal software engineering effort.
Goal and Objective: In this seminar paper, a survey about exisiting API composition approaches from a technological viewpoint is to be made. Optionally, you can also try out available matching algorithms or mapping languages by yourself.
TOPIC 4: Causal reasoning in Multi-Agent Systems
Introduction: As opposed to Data Science, Causation Theory is based on the assumption that not everything is in the data. Therefore, the difference between correlation and causation is very much emphasized, and methods of causal calculus are applied to draw conclusions from observations. In Multi-Agent Systems (MAS), understanding cause and effects of actions inherently poses an important challenge, both for agents and for any governing instance. Nevertheless, many current methods in MAS are based on data only, and equipping such systems with causal inference can possibly leverage their abilities substantially.
Goal and Objective: In this seminar, you will investigate the current state of Causation Theory in connection with Multi-Agent Systems, and you will understand the potential, the drawbacks and the challenges of this particular field of research.
|Institute for Enterprise Systems||L15, email@example.com||Office Management|
|Schloss||68131 Mannheim||+49 621 181-3560|