The goal of this project is to improve the linguistic (manual and automatic) annotation pipeline for the Sumerian language. We have developed a large range of state-of-the-art tools, dictionary, rule and ML based for each step of the process. However, we can improve most of these individual components and also the way they are combined, and the workflows involved. The ultimate goal of this project will be to make sure it is possible to start from an unannotated text and produce a good annotation of such text in a seamless manner. Most of the tools required are already deployed into our framework and the human interface is also partially integrated. Most of the work will involve writing converters, improving state of the art RDF-based annotators, combine ML tools with rules applies before and after processing to improve results, etc. Students working on this project will be invited to co-write articles as pertinent to showcase results.
