Hi Chalitha, YAGO is a very interesting knowledge base. In addition to plain Entity Linking YAGO could also be used for more advanced things like
* using its much cleaner categories (compared to dbpedia) and the "thematic domains" to categorize Documents. This could be done by training a classifier by using textual descriptions of Entities assigned to those categories. Maybe also a categorization based on linked Entities could work. * As YAGO assigns Entities with spatial and temporal regions it should be possible to detect the mentions of Events in documents (see also STANBOL-1121 related to this) As YAGO is licensed under CC Attribution it could be directly integrated in Stanbol. AIDA itself is very interesting and iterating it as a Stanbol Disambiguation engine would be great. Also [EMNLP2011] very interesting to read. However AIDAs license does make it very unattractive for a GSoC Project mentored by Apache Stanbol as we would not be able to integrate the results of this project. best Rupert [EMNLP2011]: J. Hoffart, M. A. Yosef, I. Bordino, H. Fürstenau, M. Pinkal, M. Spaniol, B. Taneva, S. Thater, and G. Weikum, "Robust Disambiguation of Named Entities in Text," Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, Edinburgh, Scotland, 2011, pp. 782–792. On Mon, Mar 3, 2014 at 5:32 PM, chalitha udara Perera <chalithaud...@gmail.com> wrote: > Hi Rupert, > > Here are the links for YAGO and AIDA. > > - http://www.mpi-inf.mpg.de/yago-naga/yago/ > - https://github.com/yago-naga/aida > > Coding part will be the integration of AIDA NED. Basically this will act as > another disambiguation engine for Stanbol. > > Looking forward for more suggestions. > > Thank You, > Chalitha Perera > > > On Mon, Mar 3, 2014 at 3:57 PM, Rupert Westenthaler < > rupert.westentha...@gmail.com> wrote: > >> Hi Chalitha, >> >> may I ask two quick question: >> >> Can you provide links to YAGO2, AIDA NED? >> What would be the coding part of such as GSOC project? >> >> best >> Rupert >> >> On Mon, Mar 3, 2014 at 6:14 AM, chalitha udara Perera >> <chalithaud...@gmail.com> wrote: >> > Hi Rafa and All, >> > >> > Thanks for ideas for GSOC 2014. I would like to proceed with Integrating >> > YAGO2 site and AIDA NED with Stanbol. But AIDA is licensed under Creative >> > Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License which >> > according to can only be used for Non-Commercial use. Would this be a >> > problem ?. >> > >> > Any advices form proceeding from here would be very appreciated. >> > >> > Thank You, >> > Chalitha Perera. >> >> >> >> -- >> | Rupert Westenthaler rupert.westentha...@gmail.com >> | Bodenlehenstraße 11 ++43-699-11108907 >> | A-5500 Bischofshofen >> -- | Rupert Westenthaler rupert.westentha...@gmail.com | Bodenlehenstraße 11 ++43-699-11108907 | A-5500 Bischofshofen