Word alignment methods can gain valuable guidance by ensuring that their alignments maintain cohesion with respect to the phrases specified by a monolingual dependency tree. Howev...
The search for relevant information is often hindered by the initial difficulty in formulating precise requests, and because much knowledge is actually tacit and thus not easily ac...
This paper describes a method for structuring a robot motor learning task. By designing a suitably parameterized policy, we show that a simple search algorithm, along with biologi...
In this paper we propose to combine two powerful ideas, boosting and manifold learning. On the one hand, we improve ADABOOST by incorporating knowledge on the structure of the dat...
We present a neural network method for inducing representations of parse histories and using these history representations to estimate the probabilities needed by a statistical le...