# Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing

arXiv: https://arxiv.org/abs/1810.10882 · HTML: https://mlsanity.com/paper/1810.10882/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2018.

## Built on by (most cited first, 2 of 2)

- [Discontinuous Grammar as a Foreign Language](https://mlsanity.com/paper/2110.10431/) (2021)
- [In-Order Chart-Based Constituent Parsing](https://mlsanity.com/paper/2102.04065/) (2021)

## Abstract (arXiv)

We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manage to notably increase their accuracy, in comparison to that obtained by performing classic static training. In addition, by improving the performance of the state-of-the-art in-order shift-reduce parser, we achieve the best accuracy to date (92.0 F1) obtained by a fully-supervised single-model greedy shift-reduce constituent parser on the WSJ benchmark.