papers AI Learner
The Github is limit! Click to go to the new site.

Top-down Tree Long Short-Term Memory Networks

2016-04-03
Xingxing Zhang, Liang Lu, Mirella Lapata

Abstract

Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks. In this paper we develop Tree Long Short-Term Memory (TreeLSTM), a neural network model based on LSTM, which is designed to predict a tree rather than a linear sequence. TreeLSTM defines the probability of a sentence by estimating the generation probability of its dependency tree. At each time step, a node is generated based on the representation of the generated sub-tree. We further enhance the modeling power of TreeLSTM by explicitly representing the correlations between left and right dependents. Application of our model to the MSR sentence completion challenge achieves results beyond the current state of the art. We also report results on dependency parsing reranking achieving competitive performance.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1511.00060

PDF

https://arxiv.org/pdf/1511.00060


Similar Posts

Comments