Projects from Kai Biermeier, M.Sc.
TRR 318 - Project A05: Contextualized and online parametrization of attention in human–robot explanatory dialog
In Project A05, researchers from the areas of linguistics, psychology, and computer science are investigating attention in human-robot explanatory dialog. They are addressing questions including: where do humans focus their attention when a robot explains a task to them? How can robots direct their counterpart’s attention to achieve the goal of the ...
Duration: 07/2021 - 12/2025
TRR 318 - Project B01: A dialog-based approach to explaining machine learning models
In Project B01, researchers are working on an artificial intelligence (AI) based system that can properly respond to questions at the level of language. In medicine, for example, the system should be able to explain a proposed treatment to a doctor and respond to patients’ questions and concerns regarding their treatment plan. The computer ...
Duration: 07/2021 - 12/2025
TRR 318 - Project C01: Healthy distrust in explanations
The focus is on crucial overarching properties of decisions and explanations. The aim is to investigate the important question of how a person’s critical attitude towards an AI system can be supported by fostering a healthy distrust in intelligent systems, and whether and how this attitude can be reinforced by means of explainable machine learning ...
Duration: 07/2021 - 12/2025
TRR 318 - Project C02: Interactive learning of explainable, situation-adapted decision models
The focus of Project C02 investigates a novel approach through which the space of possible models explaining a certain decision can be explored interactively by a user until a model is found that satisfies the needs of the user in terms of the trade-off between accuracy and model complexity. The project defines and explores a refinement relation ...
Duration: 07/2021 - 12/2025
TRR 318 - Project C04: Metaphors as an explanation tool
Project C04 investigates metaphors as a specific means to make difficult phenomena interpretable. The innovative aspect is to regard both highlighting and hiding processes when metaphors are utilized in explanations. The project aims to understand how metaphors may either facilitate or impede understanding, and how this understanding can be applied ...
Duration: 07/2021 - 12/2025
TRR 318 - Project C06: Technically enabled explanation of speaker traits
A voice might be described as hoarse, or it may be clear, deep, or breathy. Researchers in Project C06 are looking at issues of how different vocal traits sound, and how a voice can be represented in all of its many facets. Here, linguists and computer scientists are working to develop an intelligent system that professionals can use to explain the ...
Duration: 07/2021 - 12/2025
TRR 318 - Project Z: Central administrative project
The general administrative Project Z will contribute to the success of the TRR in three ways: First, it will administer both the budgeting and organization of the TRR. Second, it will co-organize the TRR workshops and conferences. Third, it will monitor the TRR’s output and evaluate the efficiency of its internal structure, also with regard to the ...
Duration: 07/2021 - 12/2025
TRR 318 - Project B05: Co-constructing explainability with an interactively learning robot
In close collaboration with Project Ö, Project B05 tackles the question of how explainability can be achieved through co-construction within learning task rather than an explicit explanation. More specifically, it investigates how explainees’ mental model about a learning robot is influenced by their gender, age, and workshops (from Project Ö that ...
Duration: 07/2021 - 12/2025
TRR 318 - Project C03: Interpretable machine learning: Explaining change
Project C03 centers on how to account for dynamic properties of an explanandum. Its target is to deliver a model that will explain a drift of data that a machine learning model undergoes over time as a result of nonstationary distributions and evolving training data. The project will go beyond a mere transfer of established methodology ...
Duration: 07/2021 - 12/2025
TRR 318 - Project C05: Creating explanations in collaborative human–machine knowledge exploration
Project C05 is concerned with developing the foundations of systems that interactively support users in exploring a decision domain to reach a decision that is explainable and accountable. The focus is on modeling the use of interventional and counterfactual inferences over domain knowledge in an explorative decision-making process. On this basis, ...
Duration: 07/2021 - 12/2025