Ph.D Fellowship in Language Modeling for Explainable AI

The University of Stavanger invites applicants for a PhD Fellowship in Language Modeling for Explainable AI at the Faculty of Science and Technology, Department of Electrical Engineering and Computer Science. The position is vacant for accession as soon as possible.

This is a trainee position that will give promising researchers an opportunity for academic development through a PhD education leading to a doctoral degree.
The hired candidate will be admitted to the PhD program in Science and Technology. The education includes relevant courses to about six months of study, a dissertation based on independent research, participation in national and international research environments, relevant academic communication, a trial lecture and public defence. Read more about the PhD education at UiS on our website.
The appointment is for three years with research duties exclusively, or four years with both research and 25% compulsory duties. This will be clarified in the recruitment process.

Stavanger is located on the southwestern coast of Norway, in the Norwegian fjord region, offering some of the most majestic and spectacular scenery in the world. At the same time, the city is within easy access with a well-developed infrastructure for both national and international travelers.
Over the past years, the University of Stavanger has acquired a strong reputation for research in AI and information retrieval. UiS hosted the 10th International Conference on the Theory of Information Retrieval (ICTIR'20) and will host the 44th European Conference on Information Retrieval (ECIR'22).
We also have ongoing collaborations with top industry players, both nationally and internationally. The position is funded by SFI NorwAI, the new 8-year research-based innovation Center for AI Innovation. Here, we are joining forces with 15 partners from industry, universities and research institutes. Research areas cover competences that the Norwegian industry needs to develop cutting-edge theories, methods and technology, for efficient, effective and responsible exploitation of data-driven AI in innovative industrial solutions.
We offer competitive salary and excellent work-life balance.

Project proposal
AI-powered systems exhibit a growing degree of personalization when recommending content. Users, however, have little knowledge of how these systems work and what personal data they use. There is a need for transparency, in terms of (1) collecting and using personal data, and how it is used for inferring user preferences and (2) explaining and justifying the generated recommendations. The most human-like form of providing explanations is via natural language. This would allow users to better understand how their preferences are understood and
interpreted by the system, and also correct it if necessary.
The main goal of the project is to develop novel models that enable semantically rich and context-dependent text-based explainability of user preferences and system recommendations, using either existing metadata or automatically extracted annotations. A starting point for generating explanations is template-based; later, this can be made more human-like using language generation techniques, using large-scale (pre-trained) language models.
The application must be accompanied by a cover letter explaining your interest in the project and the relevance of your background and experience. Applications without a cover letter will not be considered.