Syntax-Enhanced Self-Attention-Based Semantic Role Labeling

TL;DR

This paper introduces a syntax-enhanced self-attention model for semantic role labeling, demonstrating that incorporating high-quality syntactic information improves performance and achieves state-of-the-art results on Chinese SRL.

Contribution

It proposes a novel syntax-enhanced self-attention approach that effectively integrates syntactic knowledge into SRL models, outperforming existing baselines.

Findings

Achieves new state-of-the-art on Chinese SRL dataset

High-quality syntactic info significantly boosts model performance

Comparative analysis of different syntactic encoding methods

Abstract

As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence. This paper investigates how to incorporate syntactic knowledge into the SRL task effectively. We present different approaches of encoding the syntactic information derived from dependency trees of different quality and representations; we propose a syntax-enhanced self-attention model and compare it with other two strong baseline methods; and we conduct experiments with newly published deep contextualized word representations as well. The experiment results demonstrate that with proper incorporation of the high quality syntactic information, our model achieves a new state-of-the-art performance for the Chinese SRL task on the CoNLL-2009 dataset.