Dynamic Compositional Neural Networks over Tree Structure
This work addresses a specific bottleneck in compositional models for natural language processing, offering an incremental improvement over existing methods.
The paper tackles the underfitting problem in tree-structured neural networks by introducing dynamic compositional neural networks (DC-TreeNN), which use a meta-network to generate compositional functions dynamically, resulting in improved performance on two typical tasks.
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.