Bracketing Encodings for 2-Planar Dependency Parsing

TL;DR

This paper introduces a bracketing-based encoding for 2-planar dependency trees that significantly improves non-projective parsing accuracy by leveraging the property that most syntactic structures are 2-planar, enabling near-complete coverage of crossing arcs.

Contribution

The authors develop a novel bracketing encoding that handles almost all 2-planar dependency trees, overcoming previous limitations and enhancing sequence labeling parsing for non-projective structures.

Findings

Achieves around 99.9% coverage of crossing arcs in 2-planar trees.

Improves LAS by approximately 0.4 points on highly non-projective treebanks.

Maintains similar parsing speed to previous encodings.

Abstract

We present a bracketing-based encoding that can be used to represent any 2-planar dependency tree over a sentence of length n as a sequence of n labels, hence providing almost total coverage of crossing arcs in sequence labeling parsing. First, we show that existing bracketing encodings for parsing as labeling can only handle a very mild extension of projective trees. Second, we overcome this limitation by taking into account the well-known property of 2-planarity, which is present in the vast majority of dependency syntactic structures in treebanks, i.e., the arcs of a dependency tree can be split into two planes such that arcs in a given plane do not cross. We take advantage of this property to design a method that balances the brackets and that encodes the arcs belonging to each of those planes, allowing for almost unrestricted non-projectivity (round 99.9% coverage) in sequence labeling parsing. The experiments show that our linearizations improve over the accuracy of the original bracketing encoding in highly non-projective treebanks (on average by 0.4 LAS), while achieving a similar speed. Also, they are especially suitable when PoS tags are not used as input parameters to the models.