Corpus ID: 35933354

T REE-STRUCTURED DECODING WITH DOUBLY-RECURRENT NEURAL NETWORKS

@inproceedings{AlvarezMelis2017TRD,
  title={T REE-STRUCTURED DECODING WITH DOUBLY-RECURRENT NEURAL NETWORKS},
  author={David Alvarez-Melis and T. Jaakkola},
  year={2017}
}

David Alvarez-Melis, T. Jaakkola

Published 2017

We propose a neural network architecture for generating tree-structured objects from encoded representations. The core of the method is a doubly recurrent neural network model comprised of separate width and depth recurrences that are combined inside each cell (node) to generate an output. The topology of the tree is modeled explicitly together with the content. That is, in response to an encoded vector representation, co-evolving recurrences are used to realize the associated tree and the… CONTINUE READING

people.csail.mit.edu

Save to Library

Create Alert

Cite

Launch Research Feed