Learning to Compose Words into Sentences with Reinforcement Learning

international conference on learning representations, 2017.

Cited by: 121|Views111
EI
Weibo:
We demonstrated the benefit of learning task-specific composition order on four tasks: sentiment analysis, semantic relatedness, natural language inference, and sentence generation

Abstract:

We use reinforcement learning to learntree-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 orpredicted using supervision from explicit treebank annotations,the tree structures in this work are optim...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments