A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing

TL;DR

This paper introduces a dynamic oracle for the 2-Planar dependency parser, significantly improving training efficiency and accuracy across multiple languages with non-projective syntactic structures.

Contribution

It presents a novel dynamic oracle for the 2-Planar parser, enhancing training effectiveness and outperforming existing static and arc-hybrid parsers on various datasets.

Findings

Outperforms static training strategies in most languages

Achieves over 99% coverage on non-projective corpora

Scored better than arc-hybrid with SWAP transition on most datasets

Abstract

We propose an efficient dynamic oracle for training the 2-Planar transition-based parser, a linear-time parser with over 99% coverage on non-projective syntactic corpora. This novel approach outperforms the static training strategy in the vast majority of languages tested and scored better on most datasets than the arc-hybrid parser enhanced with the SWAP transition, which can handle unrestricted non-projectivity.