A Double-Graph Based Framework for Frame Semantic Parsing
This addresses frame semantic parsing for NLP applications, offering a novel integration of knowledge graphs and incremental graph construction, though it appears incremental in its approach to existing parsing tasks.
The paper tackles frame semantic parsing by proposing a double-graph framework that incorporates ontological knowledge and strengthens interactions between subtasks, achieving up to 1.7 F1-score improvement over previous state-of-the-art methods on FrameNet datasets.
Frame semantic parsing is a fundamental NLP task, which consists of three subtasks: frame identification, argument identification and role classification. Most previous studies tend to neglect relations between different subtasks and arguments and pay little attention to ontological frame knowledge defined in FrameNet. In this paper, we propose a Knowledge-guided Incremental semantic parser with Double-graph (KID). We first introduce Frame Knowledge Graph (FKG), a heterogeneous graph containing both frames and FEs (Frame Elements) built on the frame knowledge so that we can derive knowledge-enhanced representations for frames and FEs. Besides, we propose Frame Semantic Graph (FSG) to represent frame semantic structures extracted from the text with graph structures. In this way, we can transform frame semantic parsing into an incremental graph construction problem to strengthen interactions between subtasks and relations between arguments. Our experiments show that KID outperforms the previous state-of-the-art method by up to 1.7 F1-score on two FrameNet datasets. Our code is availavle at https://github.com/PKUnlp-icler/KID.