High-order Joint Constituency and Dependency Parsing

TL;DR

This paper introduces an efficient high-order joint parsing method for constituency and dependency trees, improving compatibility modeling and overall parsing performance across multiple languages.

Contribution

It proposes a novel $O(n^4)$ decoding algorithm, joint training at the modeling phase, and high-order scoring components for better constituent-dependency interaction.

Findings

Joint modeling improves complete tree matching ratio.

The $O(n^4)$ decoding algorithm is more efficient than previous methods.

Experiments on seven languages demonstrate performance gains.

Abstract

This work revisits the topic of jointly parsing constituency and dependency trees, i.e., to produce compatible constituency and dependency trees simultaneously for input sentences, which is attractive considering that the two types of trees are complementary in representing syntax. The original work of Zhou and Zhao (2019) performs joint parsing only at the inference phase. They train two separate parsers under the multi-task learning framework (i.e., one shared encoder and two independent decoders). They design an ad-hoc dynamic programming-based decoding algorithm of $O(n^5)$ time complexity for finding optimal compatible tree pairs. Compared to their work, we make progress in three aspects: (1) adopting a much more efficient decoding algorithm of $O(n^4)$ time complexity, (2) exploring joint modeling at the training phase, instead of only at the inference phase, (3) proposing high-order scoring components to promote constituent-dependency interaction. We conduct experiments and analysis on seven languages, covering both rich-resource and low-resource scenarios. Results and analysis show that joint modeling leads to a modest overall performance boost over separate modeling, but substantially improves the complete matching ratio of whole trees, thanks to the explicit modeling of tree compatibility.