# Sequential Graph Dependency Parser

## TL;DR

This paper introduces a novel set-based, transition-based dependency parsing method capable of handling both projective and non-projective languages, achieving near state-of-the-art results without fixed parsing order.

## Contribution

It presents a new set-based learning approach for non-projective dependency parsing that integrates graph, transition, and easy-first parsing techniques.

## Key findings

- Achieves near state-of-the-art accuracy on multiple languages.
- Effectively handles both projective and non-projective dependencies.
- Does not assume a fixed parsing order.

## Abstract

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The proposed transition-based method successfully parses near the state of the art on both projective and non-projective languages, without assuming a certain parsing order.