CCing the mailing list for transparency. On 3/20/14, 2:12 PM, Sanmaya Jolly wrote: > Thanks Marco, > > The wiki helped me out there too. I'm currently studying the paper [1] > mentioned about using weights to check the correctness of the type and > property that best describe instances of classes and the working of RDF [2]. > I believe that by accommodating basic NLP concepts into the already > documented statistical machine learning (supervised), we can identify > more properties that can enhance the process of inferring the type or > subclass a resource may belong to. This is currently being performed on > the infobox data but extending it to other parts (like the introduction > or overview) would provide another stepping stone to more accurate > knowledge completion. Have a look at this paper [1], it applies NLP techniques for type inference. Also, @Milan (in CC) is working on a NLP-based approach.
[1] http://iswc2012.semanticweb.org/sites/default/files/76490065.pdf > > Could you please guide me regarding the kind of architecture that is > being asked for in the project proposal? Would it be an > implementation-level description (with the specifics) or just a holistic > view of the methodologies involved in the solving of such a problem? Both, but try to think pragmatic and focus on the actual implementation. > > [1] http://www.heikopaulheim.com/documents/iswc2013.pdf > [2] http://www.w3.org/TR/2014/REC-rdf11-concepts-20140225/ > > Best, > > Sanmaya -- Marco Fossati http://about.me/marco.fossati Twitter: @hjfocs Skype: hell_j ------------------------------------------------------------------------------ Learn Graph Databases - Download FREE O'Reilly Book "Graph Databases" is the definitive new guide to graph databases and their applications. Written by three acclaimed leaders in the field, this first edition is now available. Download your free book today! http://p.sf.net/sfu/13534_NeoTech _______________________________________________ Dbpedia-gsoc mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc
