On Thursday night I gave a talk titled "Machine Learning Techniques for the Semantic Web" at the Semantic Web Meetup. As promised I'm posting my slides and pointers to some research papers I read in preparation for the talk.
Papers
- Ontology Mapping: A Machine Learning Approach by AH Doan, J Madhavan, P Domingos, A Halevy
- Towards Machine Learning on the Semantic Web by Volker Tresp, Markus Bundschus, Achim Rettinger, and Yi Huang
- Ontology Learning from Text: A Survey of Methods by Chris Biemann
- Generalized Hebbian Algorithm for Incremental Singular Value Decomposition in Natural Language Processing by Genevieve Gorrell
There were others, but those should be enough to get anyone interested in the topic started. The second two have a lot of pointers in the references section to more good reading. The last paper on SVD is useful when doing latent factors analysis on very large, sparse matrices. Competitors in the Netflix prize have used variations on the algorithm to achieve some impressive results.
Finally, here are the slides.
Machine Learning Techniques for the Semantic Web
View more presentations from pauldix.
Second paper should be http://wwwbrauer.in.tum.de/~trespvol/papers/LearningRDF23.pdf
Posted by: james | April 15, 2009 at 05:02 PM