Abstract. We consider the problem of learning stochastic tree languages, i.e. probability distributions over a set of trees T(F), from a sample of trees independently drawn accordi...
We focus on the estimation of a probability distribution over a set of trees. We consider here the class of distributions computed by weighted automata - a strict generalization of...
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...