Building a prototype for a shared digital assistant is one of the identified tasks to support the use of AI in the public sector. In this project we explore and identify how the prototype should be designed in order to be easy to use and accessible to every staff member, regardless of their technical skills. 

Examples of tasks the assistant could be able to help with:

• Summarize and analyze large amounts of text
• Improve and edit texts to make them more readable and structured
• Create new texts such as reports, documents, and applications, customized according to specific templates and guidelines
• Classify documents and create decision support in administrative processes
• Develop personalized support to assist citizens best

Bahar Safari

My  part in this project involves analyzing and improving a machine-translated dataset from English to Swedish. Annotators review questions and answers to correct language errors and make the text more culturally relevant for a Swedish audience. We have two datasets and the objectives are

• Any patterns in why questions are skipped
• Reasons for excluding certain questions
• Differences between the original and edited versions, focusing on language quality and cultural relevance