Active Relation Discovery: Towards General and Label-aware Open Relation Extraction
This work improves OpenRE for applications requiring discovery and labeling of novel relations from open domains, though it is incremental as it builds on existing methods to address specific bottlenecks.
The paper tackles the problem of Open Relation Extraction (OpenRE) by addressing two key issues: discriminating between known and novel relations in general settings and providing human-readable labels for novel relations, resulting in ARD significantly outperforming previous state-of-the-art methods on three real-world datasets.
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.