Recent models have shown that incorporating syntactic knowledge into the semantic role labelling (SRL) task leads to a significant improvement. In this paper, we propose Syntax-aware Graph-to-Graph Transformer (SynG2G-Tr) model, which encodes the syntactic structure using a novel way to input graph relations as embeddings, directly into the self-attention mechanism of Transformer. This approach adds a soft bias towards attention patterns that follow the syntactic structure but also allows the model to use this information to learn alternative patterns. We evaluate our model on both span-based and dependency-based SRL datasets, and outperform previous alternative methods in both in-domain and out-of-domain settings, on CoNLL 2005 and CoNLL 2009 datasets.
@article{arxiv.2104.07704,
title = {Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling},
author = {Alireza Mohammadshahi and James Henderson},
journal= {arXiv preprint arXiv:2104.07704},
year = {2023}
}