A Higher-Order Semantic Dependency Parser

TL;DR

This paper introduces a novel higher-order semantic dependency parser that leverages graph neural networks to efficiently incorporate complex features, achieving state-of-the-art results on benchmark datasets.

Contribution

It proposes using stacked GNN layers to implicitly model higher-order features in semantic parsing, avoiding NP-hard explicit inference.

Findings

Outperforms previous state-of-the-art parsers on SemEval 2015 datasets

Demonstrates effectiveness of GNNs in semantic dependency parsing

Shows that implicit higher-order feature modeling improves accuracy

Abstract

Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for solving NP-hard problems with approximate inference in many graph learning tasks. Inspired by the success of GNNs, we investigate building a higher-order semantic dependency parser by applying GNNs. Instead of explicitly extracting higher-order features from intermediate parsing graphs, GNNs aggregate higher-order information concisely by stacking multiple GNN layers. Experimental results show that our model outperforms the previous state-of-the-art parser on the SemEval 2015 Task 18 English datasets.