# Transferring Neural Potentials For High Order Dependency Parsing

arXiv: https://arxiv.org/abs/2306.10469 · HTML: https://mlsanity.com/paper/2306.10469/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 18 Jun 2023.

## Builds on (most cited first, 7 of 7)

- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Stack-Pointer Networks for Dependency Parsing](https://mlsanity.com/paper/1805.01087/) (2018)
- [LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction](https://mlsanity.com/paper/2001.04437/) (2020)
- [Dependency Parsing as MRC-based Span-Span Prediction](https://mlsanity.com/paper/2105.07654/) (2021)
- [Approximation-Aware Dependency Parsing by Belief Propagation](https://mlsanity.com/paper/1508.02375/) (2015)
- [On Finding the K-best Non-projective Dependency Trees](https://mlsanity.com/paper/2106.00780/) (2021)
- [Edge-Linear First-Order Dependency Parsing with Undirected Minimum Spanning Tree Inference](https://mlsanity.com/paper/1510.07482/) (2015)

## Abstract (arXiv)

High order dependency parsing leverages high order features such as siblings or grandchildren to improve state of the art accuracy of current first order dependency parsers. The present paper uses biaffine scores to provide an estimate of the arc scores and is then propagated into a graphical model. The inference inside the graphical model is solved using dual decomposition. The present algorithm propagates biaffine neural scores to the graphical model and by leveraging dual decomposition inference, the overall circuit is trained end-to-end to transfer first order informations to the high order informations.