A library for developing portable applications that deal with networking, threads (message passing, futures, etc...), graphical interfaces, complex data structures, linear algebra,...
Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation...
Ofer Meshi, David Sontag, Tommi Jaakkola, Amir Glo...
While discriminative training (e.g., CRF, structural SVM) holds much promise for machine translation, image segmentation, and clustering, the complex inference these applications ...
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...