Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering

TL;DR

This paper introduces a method to convert discontinuous parsing problems into continuous ones using a Pointer Network, enabling the use of existing continuous parsers for faster and accurate discontinuous parsing.

Contribution

The paper presents a novel approach that reduces discontinuous parsing to a continuous problem via token reordering, leveraging Pointer Networks for improved speed and competitive accuracy.

Findings

Achieves comparable accuracy to state-of-the-art discontinuous parsers.

Significantly improves parsing speed.

Effectively leverages off-the-shelf continuous parsers.

Abstract

Discontinuous constituent parsers have always lagged behind continuous approaches in terms of accuracy and speed, as the presence of constituents with discontinuous yield introduces extra complexity to the task. However, a discontinuous tree can be converted into a continuous variant by reordering tokens. Based on that, we propose to reduce discontinuous parsing to a continuous problem, which can then be directly solved by any off-the-shelf continuous parser. To that end, we develop a Pointer Network capable of accurately generating the continuous token arrangement for a given input sentence and define a bijective function to recover the original order. Experiments on the main benchmarks with two continuous parsers prove that our approach is on par in accuracy with purely discontinuous state-of-the-art algorithms, but considerably faster.