Hi Chalitha, Thanks for coming back to Stanbol after GSoC!! I have in my TODO list to deeply review the code and merge it into Stanbol. If you are planning to make more improvements, we can leave for now in a branch that can be included in the trunk when it will be mature enough.
Using the project outcome as baseline, I can suggest a first list of possible improvements: 1. Extend Aida-Light for supporting others datasets. We would need to check how much the disambiguation algorithms are coupled with the information provided by YAGO and try to convert them to a generic approach. 2. Current Aida-Light architecture. Currently, all the data is preloaded in memory forcing the user to use a high profiled machines. We have discussed this several times, but maybe it is moment to finally decide on a proper backend strategy for supporting disambiguation. Probably current Yards are not enough/valid. 3. Stanbol Disambiguation API. Another (almost) eternal discussion. Can we design an extensible API for supporting different disambiguation approaches? I will start by creating the branch ASAP Chalitha. Thanks!! Cheers, Rafa En 23 de octubre de 2014 en 9:28:35, chalitha udara Perera (chalithaud...@gmail.com) escrito: Hi all, As you know, For GSOC I have integrated YAGO knowledge base and Aida-light disambiguation server with Stanbol. But there are many improvements that can be applied to current disambiguation engine. For example current engine only works with YAGO site, but it would be more useful if it support other sites such as dbpedia. I would like to continue contributing to Stanbol. As mentioned above I can start with making disambiguation engine to used with dbpedia entities. What you guys think ? Any feedback will be greatly appreciated. cheers, Chalitha -- J.M Chalitha Udara Perera *Department of Computer Science and Engineering,* *University of Moratuwa,* *Sri Lanka*