Active Relation Discovery: Towards General and Label-aware Open Relation Extraction

TL;DR

This paper introduces Active Relation Discovery (ARD), a framework that improves open relation extraction by effectively identifying and labeling novel relations through outlier detection and active learning, outperforming previous methods.

Contribution

The paper presents ARD, a novel framework combining outlier detection and active learning to better discriminate and label novel relations in open relation extraction.

Findings

ARD outperforms previous state-of-the-art methods.

Effective discrimination between known and novel relations.

Significant improvements in general OpenRE settings.

Abstract

Open Relation Extraction (OpenRE) aims to discover novel relations from open domains. Previous OpenRE methods mainly suffer from two problems: (1) Insufficient capacity to discriminate between known and novel relations. When extending conventional test settings to a more general setting where test data might also come from seen classes, existing approaches have a significant performance decline. (2) Secondary labeling must be performed before practical application. Existing methods cannot label human-readable and meaningful types for novel relations, which is urgently required by the downstream tasks. To address these issues, we propose the Active Relation Discovery (ARD) framework, which utilizes relational outlier detection for discriminating known and novel relations and involves active learning for labeling novel relations. Extensive experiments on three real-world datasets show that ARD significantly outperforms previous state-of-the-art methods on both conventional and our proposed general OpenRE settings. The source code and datasets will be available for reproducibility.