EPPAC: Entity Pre-typing Relation Classification with Prompt AnswerCentralizing

TL;DR

EPPAC introduces a novel prompt-based relation classification method that pre-types entities and centralizes prompt answers, significantly improving performance on TACRED and TACREV datasets.

Contribution

The paper proposes EPPAC, a new paradigm combining entity pre-typing and prompt answer centralizing to enhance relation classification accuracy.

Findings

EPPAC outperforms state-of-the-art methods on TACRED and TACREV.

Entity pre-typing improves relation classification performance.

Prompt answer centralizing reduces manual prompt design effort.

Abstract

Relation classification (RC) aims to predict the relationship between a pair of subject and object in a given context. Recently, prompt tuning approaches have achieved high performance in RC. However, existing prompt tuning approaches have the following issues: (1) numerous categories decrease RC performance; (2) manually designed prompts require intensive labor. To address these issues, a novel paradigm, Entity Pre-typing Relation Classification with Prompt Answer Centralizing(EPPAC) is proposed in this paper. The entity pre-tying in EPPAC is presented to address the first issue using a double-level framework that pre-types entities before RC and prompt answer centralizing is proposed to address the second issue. Extensive experiments show that our proposed EPPAC outperformed state-of-the-art approaches on TACRED and TACREV by 14.4% and 11.1%, respectively. The code is provided in the Supplementary Materials.