Dynamic Compositional Neural Networks over Tree Structure

by Pengfei Liu, Xipeng Qiu, Xuanjing Huang


Fig. (a) Dynamic compositional neural network, where θ denotes the context-dependent parameters generated by meta TreeNN. (b) Dynamic matching network.


Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information. In spite of their success, most existing models suffer from the underfitting problem: they recursively use the same shared compositional function throughout the whole compositional process and lack expressive power due to inability to capture the richness of compositionality. In this paper, we address this issue by introducing the dynamic compositional neural networks over tree structure (DC-TreeNN), in which the compositional function is dynamically generated by a meta network. The role of meta-network is to capture the metaknowledge across the different compositional rules and formulate them. Experimental results on two typical tasks show the effectiveness of the proposed models.

Case Analysis

Fig. A heat map describes the behaviour of neurons z(27) from DC-TreeNN