A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach
This addresses the limitation of current relation extraction methods in capturing complex knowledge for AI and NLP applications, though it is incremental as it builds on table-filling approaches.
The authors tackled the problem of extracting hyper-relational facts, which include qualifiers like time or location, from text to enhance knowledge graphs, and proposed CubeRE, a cube-filling model that outperforms baselines on the new HyperRED dataset.
Relation extraction has the potential for large-scale knowledge graph construction, but current methods do not consider the qualifier attributes for each relation triplet, such as time, quantity or location. The qualifiers form hyper-relational facts which better capture the rich and complex knowledge graph structure. For example, the relation triplet (Leonard Parker, Educated At, Harvard University) can be factually enriched by including the qualifier (End Time, 1967). Hence, we propose the task of hyper-relational extraction to extract more specific and complete facts from text. To support the task, we construct HyperRED, a large-scale and general-purpose dataset. Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities. Hence, we propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers. To improve model scalability and reduce negative class imbalance, we further propose a cube-pruning method. Our experiments show that CubeRE outperforms strong baselines and reveal possible directions for future research. Our code and data are available at github.com/declare-lab/HyperRED.