Deriving kernels from MLP probability estimators for large categorization problems

Ivan Titov, James Henderson

Abstract: In multi-class categorization problems with a very large or unbounded number of classes, it is often not computationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained multilayer perceptron probability estimators to derive appropriate kernels for such problems. We propose a kernel derivation method which is specifically designed for reranking problems, and a more efficient variant of this method which is specifically designed for neural networks with large numbers of output units. When applied to a neural network model of natural language parsing, these new methods achieve state-of-the-art performance which improves over the original model.

External IDs:dblp:conf/ijcnn/TitovH05