Multitask Pointer Network for Multi-Representational Parsing

TL;DR

This paper introduces a multitask Pointer Network that efficiently parses sentences into both constituent and dependency trees, supporting various syntactic structures, and achieves state-of-the-art results on multiple benchmarks.

Contribution

It presents the first unified model capable of jointly producing constituent and dependency trees for both continuous and discontinuous structures.

Findings

Achieved state-of-the-art accuracy on English and Chinese Penn Treebanks.

Successfully parsed German NEGRA and TIGER datasets with high accuracy.

Demonstrated mutual benefits for syntactic formalisms during joint training.

Abstract

We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning strategy to jointly train them. The resulting quadratic system, not only becomes the first parser that can jointly produce both unrestricted constituent and dependency trees from a single model, but also proves that both syntactic formalisms can benefit from each other during training, achieving state-of-the-art accuracies in several widely-used benchmarks such as the continuous English and Chinese Penn Treebanks, as well as the discontinuous German NEGRA and TIGER datasets.