Dependency Parsing as Head Selection. (arXiv:1606.01280v1 [cs.CL])
Conventional dependency parsers rely on a statistical model and a transition system or graph algorithm to enforce tree-structured outputs during training and inference. In this work we formalize dependency parsing as the problem of selecting the head (a.k.a. parent) of each word in a sentence. Our model which we call DeNSe (as shorthand for Dependency Neural Selection) employs bidirectional recurrent neural networks for the head selection task.