# A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network

arXiv: https://arxiv.org/abs/1505.05667 · HTML: https://mlsanity.com/paper/1505.05667/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2015.

## Built on by (most cited first, 3 of 3)

- [Modeling Diagnostic Label Correlation for Automatic ICD Coding](https://mlsanity.com/paper/2106.12800/) (2021)
- [On Finding the K-best Non-projective Dependency Trees](https://mlsanity.com/paper/2106.00780/) (2021)
- [Extracting Relational Triples Based on Graph Recursive Neural Network via Dynamic Feedback Forest Algorithm](https://mlsanity.com/paper/2308.11411/) (2023)

## Abstract (arXiv)

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.