Ethical Chatbots
Development of an ethical dialogue system, with a case study on COVID-19 vaccine information.
Research Bundles
"Research bundles" give you a space in the AI on-demand platform where you can collect and publish the outputs of a small research project in a compact way. A research bundle collects in a single place all the assets (code, data, tutorials, examples, ...) produced by your project and published on the AI on-demand platform. Of course, you can also put links to assets published elsewhere, like Github or Zenodo.
Ethical implications of language use with special consideration of the Ethics Guidelines for Trustworthy AI
This project raises ethical questions about the language we use to talk about AI and the human-AI interaction.
Explaining Crash Predictions on Multivariate Time Series Data
X-AI techniques applied to a DL model used to check real-time multivariate time series from connected black-boxes installed on cars.
Exploring the impact of Agency on Human-Computer Partnerships
The understanding of agency is a key factor in achieving realistic collaboration for human-centred Al research. Especially when designing complex interactions, like in creative or health contexts, the role the system plays can have crucial impact on the i...
Feasibility analysis of hardware acceleration for AML
This microproject investigated the feasibility of various hardware options particularly in-memory processing hardware acceleration
Human Behavior is a matter of Time! Modeling Events Interactions through Temporal Processes
The micro-project investigated recent machine and deep learning-based methods for modeling event interactions through temporal processes.
In Sync
Synchronization in interaction between Humans and Embodied AI Systems
Intelligent Virtual Characters to Induce Positive Emotions
We researched how virtual characters can be used to enhance the emotional experience people have in virtual group interaction.
Interactive Reinforcement Learning for Humorous Agents
This project aims at investigating the construction of humor models to enrich conversational agents through the help of interactive reinforcement learning approaches.
Linking language and semantic memory for building narratives
We developed an interface between an existing IRL implementation and an existing knowledge-graph reasoning engine to test if modern large-scale knowledge graphs can help resolve interpretation ambiguities.