Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling

TL;DR

This paper introduces AGED, a query-based framework for Frame Semantic Role Labeling that leverages FrameNet definitions to improve argument identification and role classification, outperforming previous methods especially in zero-shot and few-shot scenarios.

Contribution

The paper presents a novel query-based approach using FrameNet definitions to enhance FSRL, capturing label semantics and argument interactions for better performance.

Findings

Outperforms previous state-of-the-art by up to 1.3 F1-score.

Demonstrates strong generalization in zero-shot and few-shot scenarios.

Effective use of FrameNet definitions improves argument identification.

Abstract

Frame Semantic Role Labeling (FSRL) identifies arguments and labels them with frame semantic roles defined in FrameNet. Previous researches tend to divide FSRL into argument identification and role classification. Such methods usually model role classification as naive multi-class classification and treat arguments individually, which neglects label semantics and interactions between arguments and thus hindering performance and generalization of models. In this paper, we propose a query-based framework named ArGument Extractor with Definitions in FrameNet (AGED) to mitigate these problems. Definitions of frames and frame elements (FEs) in FrameNet can be used to query arguments in text. Encoding text-definition pairs can guide models in learning label semantics and strengthening argument interactions. Experiments show that AGED outperforms previous state-of-the-art by up to 1.3 F1-score in two FrameNet datasets and the generalization power of AGED in zero-shot and fewshot scenarios. Our code and technical appendix is available at https://github.com/PKUnlp-icler/AGED.