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,...

詳細記述

書誌詳細
主要な著者: Yogatama, D, Blunsom, P, Dyer, C, Grefenstette, E, Ling, W
フォーマット: Journal article
出版事項: International Conference on Learning Representations 2017

類似資料