Frame semantic parsing is a fundamental task in natural language processing.Most of the previous resear-ches are focused on the design of the single-target model.This paper designs a frame semantic parsing model for multiple targets which jointly predicts the results of multiple targets.We model and achieve the bidirectional interac-tion among the subtasks of frame semantic parsing.Moreover,Relational Graph Convolution Network(R-GCN)is utilized to encode the frame relation information,which is a way to exploit frame semantic knowledge into our mod-el.The experiments show that our model maintains good performance without extra training corpus.
维普
万方数据