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,...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Yogatama, D, Blunsom, P, Dyer, C, Grefenstette, E, Ling, W
Formáid: Journal article
Foilsithe / Cruthaithe: International Conference on Learning Representations 2017

Míreanna comhchosúla