Interactive Natural Language Technology for Explainable Artificial Intelligence
In the NL4XAI project we face the challenge of making AI self-explanatory and thus contributing to translate knowledge into products and services for economic and social benefit, with the support of Explainable AI (XAI) systems. Moreover, the focus of NL4XAI is in the automatic generation of interactive explanations in natural language (NL), as humans naturally do, and as a complement to visualization tools.
NL4XAI trains 11 creative, entrepreneurial and innovative early-stage researchers (PhD students), who are expected to leverage the use of AI models and techniques even by non-expert users. The project consortium consists of 10 beneficiaries and 9 partner organizations.
NL4XAI @HMI
At HMI, our specific objectives within NL4XAI are to define, implement and evaluate communicative strategies for the generation of interactive, personalized explanations by conversational agents. As a starting point we take the alignment mechanism that occurs in conversation between humans: the tendency to copy various aspects of each other’s language such as syntactic structure and word choice, and to mirror each other’s non-verbal behaviour. We will investigate whether using alignment to tailor the way explanations are presented to the user by conversational agents, will improve comprehensibility of the explanations.
Link to project website: https://nl4xai.eu/
People involved at HMI
- Sumit Srivasatava, MSc.: s.srivastava-1@utwente.nl
- Dr. Mariët Theune: m.theune@utwente.nl
