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,...
Main Authors: | Yogatama, D, Blunsom, P, Dyer, C, Grefenstette, E, Ling, W |
---|---|
格式: | Journal article |
出版: |
International Conference on Learning Representations
2017
|
相似书籍
-
A convolutional neural network for modelling sentences
由: Kalchbrenner, N, et al.
出版: (2014) -
A Convolutional Neural Network for Modelling Sentences
由: Kalchbrenner, N, et al.
出版: (2014) -
Emergency of sentences reading composed by numerals and taught words
由: José Gonçalves Medeiros, et al.
出版: (2007-11-01) -
Generative and discriminative text classification with recurrent neural networks
由: Yogatama, D, et al.
出版: (2017) -
Learning Bilingual Word Representations by Marginalizing Alignments
由: Kočiský, T, et al.
出版: (2014)