# A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing

arXiv: https://arxiv.org/abs/1706.03367 · HTML: https://mlsanity.com/paper/1706.03367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2017.

## Built on by (most cited first, 1 of 1)

- [On the Challenges of Fully Incremental Neural Dependency Parsing](https://mlsanity.com/paper/2309.16254/) (2023)

## Abstract (arXiv)

Restricted non-monotonicity has been shown beneficial for the projective arc-eager dependency parser in previous research, as posterior decisions can repair mistakes made in previous states due to the lack of information. In this paper, we propose a novel, fully non-monotonic transition system based on the non-projective Covington algorithm. As a non-monotonic system requires exploration of erroneous actions during the training process, we develop several non-monotonic variants of the recently defined dynamic oracle for the Covington parser, based on tight approximations of the loss. Experiments on datasets from the CoNLL-X and CoNLL-XI shared tasks show that a non-monotonic dynamic oracle outperforms the monotonic version in the majority of languages.