Work packages and project plan
The project work is divided into several work packages.
Work package 1: Project coordination
- Continuous collaboration and coordination with the other NLP projects; Language Models for Swedish Authorities, Swedish Medical Language Data Lab, and SuperLim
Work package 2: Data access
- (Ongoing) Need and requirement analysis among members of SKR
Work package 3: Annotation
- (Ongoing) Iteration of annotation guidelines for the sentiment analysis, including evaluation of the guidelines from the spoken dialogue perspective
- (Ongoing) Annotation of data
Work package 4: Licenses, integrity, and intellectual property rights
- (Ongoing) The technical procedure for distribution of the NER model is to be decided
- (Ongoing) Project learnings so far about the process for sharing models and data in terms of GDPR and IP rights is to be shared
Work package 5: Data Factory, adjustment, and development
- (Ongoing) The technical, legal, and ethical framework for distribution of data and models in the Data Factory is under development. Read more about it under 'What we do'.
Work package 6: Models for named entity recognition (NER) and sentiment analysis
- December 2019: A first reference group meeting was held where the NER model was presented, along with an evaluation of the model from the perspective of spoken dialogue. Presentations were also given by the stakeholders and experts.
- (Ongoing) NER model to be shared
- (Ongoing) Development of the sentiment analysis model
Work package 7: Models trained on background data
- (Ongoing) Starting the pilot on developing a solution for developers to train models without accessing the data
Work package 8: Prestudies
- November 2019: The preliminary study on language data specific to the medical domain was completed and resulted in another project funded by Vinnova: The Swedish Medical Language Data Lab.
- Spring 2021: Starting up the preliminary study on data specific to the legal domain