Attentive Semantic Role Labeling with Boundary Indicator

TL;DR

This paper proposes auxiliary boundary indicator tags for dependency-based semantic role labeling, enhancing a syntax-agnostic multi-hop self-attention model that achieves competitive results on CoNLL-2009 benchmarks for English and Chinese.

Contribution

It introduces auxiliary boundary indicator tags to improve syntax-agnostic SRL models with multi-hop self-attention, achieving competitive performance.

Findings

Achieves state-of-the-art performance on CoNLL-2009 benchmarks

Enhances syntax-agnostic models with auxiliary boundary tags

Effective for both English and Chinese SRL

Abstract

The goal of semantic role labeling (SRL) is to discover the predicate-argument structure of a sentence, which plays a critical role in deep processing of natural language. This paper introduces simple yet effective auxiliary tags for dependency-based SRL to enhance a syntax-agnostic model with multi-hop self-attention. Our syntax-agnostic model achieves competitive performance with state-of-the-art models on the CoNLL-2009 benchmarks both for English and Chinese.