Syntax-aware Multilingual Semantic Role Labeling

TL;DR

This paper introduces a syntax-guided multilingual semantic role labeling model that effectively integrates syntactic information and contextualized word representations, achieving state-of-the-art results across seven languages.

Contribution

It proposes a novel syntax-guided argument pruning method and a unified multilingual SRL model with enhanced syntax integration, addressing the gap in multilingual SRL research.

Findings

Achieves new state-of-the-art results on CoNLL-2009 benchmarks for seven languages.

Demonstrates the effectiveness of syntactic role integration across multiple languages.

Validates the benefit of deep enhanced representations for multilingual SRL.

Abstract

Recently, semantic role labeling (SRL) has earned a series of success with even higher performance improvements, which can be mainly attributed to syntactic integration and enhanced word representation. However, most of these efforts focus on English, while SRL on multiple languages more than English has received relatively little attention so that is kept underdevelopment. Thus this paper intends to fill the gap on multilingual SRL with special focus on the impact of syntax and contextualized word representation. Unlike existing work, we propose a novel method guided by syntactic rule to prune arguments, which enables us to integrate syntax into multilingual SRL model simply and effectively. We present a unified SRL model designed for multiple languages together with the proposed uniform syntax enhancement. Our model achieves new state-of-the-art results on the CoNLL-2009 benchmarks of all seven languages. Besides, we pose a discussion on the syntactic role among different languages and verify the effectiveness of deep enhanced representation for multilingual SRL.