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

TL;DR

This paper introduces dynamic oracles for top-down and in-order shift-reduce parsers, significantly improving their accuracy and setting new state-of-the-art results on the WSJ benchmark.

Contribution

It presents novel dynamic oracles for two shift-reduce parsing algorithms, enhancing their training and overall performance.

Findings

Dynamic oracles increase parser accuracy.

Achieved 92.0 F1 on WSJ benchmark.

Set new state-of-the-art for greedy shift-reduce parser.

Abstract

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.