Schema-adaptable Knowledge Graph Construction

Hongbin Ye, Honghao Gui, Xin Xu, Xi Chen, Huajun Chen, Ningyu Zhang

Submission Type: Regular Long Paper

Submission Track: Information Extraction

Submission Track 2: Resources and Evaluation

Keywords: Knowledge Graph Construction, Information Extraction

TL;DR: We propose a new task called schema-adaptable KG Construction, which aims to continually extract knowledge based on a dynamically changing schema graph without re-training.

Abstract: Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessitates a system that can handle evolving schema automatically to extract information for KGC. To address this need, we propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training. We first split and convert existing datasets based on three principles to build a benchmark, i.e., horizontal schema expansion, vertical schema expansion, and hybrid schema expansion; then investigate the schema-adaptable performance of several well-known approaches such as Text2Event, TANL, UIE and GPT-3.5. We further propose a simple yet effective baseline dubbed AdaKGC, which contains schema-enriched prefix instructor and schema-conditioned dynamic decoding to better handle evolving schema. Comprehensive experimental results illustrate that AdaKGC can outperform baselines but still have room for improvement. We hope the proposed work can deliver benefits to the community.

Submission Number: 542