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,...
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
-
A convolutional neural network for modelling sentences
著者:: Kalchbrenner, N, 等
出版事項: (2014) -
A Convolutional Neural Network for Modelling Sentences
著者:: Kalchbrenner, N, 等
出版事項: (2014) -
Emergency of sentences reading composed by numerals and taught words
著者:: José Gonçalves Medeiros, 等
出版事項: (2007-11-01) -
Generative and discriminative text classification with recurrent neural networks
著者:: Yogatama, D, 等
出版事項: (2017) -
Learning Bilingual Word Representations by Marginalizing Alignments
著者:: Kočiský, T, 等
出版事項: (2014)