An implementation (in pyTorch and MXNet) of the N-ary Tree LSTM described in the paper Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks,Kai Sheng Tai, Richard Socher, and Christopher Manning.

Note: "For large values of N (the allowed maximum number of child), these additional parameters are impractical and may be tied or fixed to zero."

This N-aryTreeLSTM can be use to process the Syntax Tree:

Requirements:

• mxnet
• nltk

Usage example:

encoder = N_aryTreeLstm()

encoder.initialize(ctx=ctx)

c, h = self.encoder(tree, inputs, 0, ctx)