A Double-Graph Based Framework for Frame Semantic Parsing

TL;DR

This paper introduces KID, a novel graph-based framework for frame semantic parsing that leverages knowledge graphs and semantic graphs to improve subtask interactions and overall accuracy.

Contribution

It proposes a double-graph approach combining Frame Knowledge Graph and Frame Semantic Graph to enhance frame semantic parsing performance.

Findings

Outperforms previous state-of-the-art by up to 1.7 F1-score

Effectively models subtask interactions and argument relations

Demonstrates improved accuracy on FrameNet datasets

Abstract

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.