Learning to compose words into sentences with reinforcement learning

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or predicted using supervision from explicit treebank annotations,...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron: Yogatama, D, Blunsom, P, Dyer, C, Grefenstette, E, Ling, W
Fformat: Journal article
Cyhoeddwyd: International Conference on Learning Representations 2017

Eitemau Tebyg