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,...

Полное описание

Библиографические подробности
Главные авторы: Yogatama, D, Blunsom, P, Dyer, C, Grefenstette, E, Ling, W
Формат: Journal article
Опубликовано: International Conference on Learning Representations 2017

Схожие документы