HETEROGENEOUS SYNTAX-AWARE SEMANTIC ROLE LABELING BASED ON GRAPH CONVOLUTIONAL NETWORKS

Recently, syntax-aware neural semantic role labeling (SRL) has received much attention. However, most of previous syntax-aware SRL works exploit homogeneous syntactic knowledge from a single syntactic treebank. Considering several high-quality publicly available Chinese syntactic treebanks, this paper proposes to extend graph convolutional networks (GCNs) for encoding heterogeneous syntactic knowledge in the heterogeneous dependency trees and makes a through comparison on various encoding methods to improve SRL performance. This model achieved 84.16 and 85.30 F1 on CPB 1.0 and CONLL-2009 Chinese data sets, respectively, both outperforming the corresponding homogeneous syntax-aware SRL models and significantly improving the performance of previous methods.