Encoder-Decoder Based Unified Semantic Role Labeling with Label-Aware Syntax

Currently the unified semantic role labeling (SRL) that achieves predicate identification and argument role labeling in an end-to-end manner has received growing interests. Recent works show that leveraging the syntax knowledge significantly enhances the SRL performances. In this paper, we investigate a novel unified SRL framework based on the sequence-to-sequence architecture with double enhancement in both the encoder and decoder sides. In the encoder side, we propose a novel label-aware graph convolutional network (LA-GCN) to encode both the syntactic dependent arcs and labels into BERT-based word representations. In the decoder side, we creatively design a pointer-network-based model for detecting predicates, arguments and roles jointly. Our pointernet decoder is able to make decisions by consulting all the input elements in a global view, and meanwhile it is syntacticaware by incorporating the syntax information from LAGCN. Besides, a high-order interacted attention is introduced into the decoder for leveraging previously recognized triplets to help the current decision. Empirical experiments show that our framework significantly outperforms all existing graphbased methods on the CoNLL09 and Universal Proposition Bank datasets. In-depth analysis demonstrates that our model can effectively capture the correlations between syntactic and SRL structures.