A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network
This work addresses dependency parsing for natural language processing, offering incremental improvements through a novel hybrid method.
The authors tackled the problem of modeling nodes in dependency trees with dense representations by proposing a recursive convolutional neural network (RCNN) architecture, which improved state-of-the-art dependency parsing on English and Chinese datasets.
In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and compositional-semantic representations of phrases and words in a dependency tree. Different with the original recursive neural network, we introduce the convolution and pooling layers, which can model a variety of compositions by the feature maps and choose the most informative compositions by the pooling layers. Based on RCNN, we use a discriminative model to re-rank a $k$-best list of candidate dependency parsing trees. The experiments show that RCNN is very effective to improve the state-of-the-art dependency parsing on both English and Chinese datasets.