Top-down Tree Long Short-Term Memory Networks
This work addresses the problem of structured prediction in natural language processing for tasks like sentence completion and parsing, representing an incremental improvement by extending LSTM to tree structures.
The paper tackled the problem of predicting dependency trees for sentences by developing TreeLSTM, a neural network model based on LSTM, and achieved results beyond the current state of the art on the MSR sentence completion challenge, with competitive performance on dependency parsing reranking.
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.