Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion

Abstract

We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns. First, each testing sample is predictable with supportive data in the training set. To ensure it, we propose to utilize rule-guided train/test generation, instead of conventional random split. Second, InferWiki initiates the evaluation following the open-world assumption and improves the inferential difficulty of the closed-world assumption, by providing manually annotated negative and unknown triples. Third, we include various inference patterns (e.g., reasoning path length and types) for comprehensive evaluation. In experiments, we curate two settings of InferWiki varying in sizes and structures, and apply the construction process on CoDEx as comparative datasets. The results and empirical analyses demonstrate the necessity and high-quality of InferWiki. Nevertheless, the performance gap among various inferential assumptions and patterns presents the difficulty and inspires future research direction. Our datasets can be found in https://github.com/TaoMiner/inferwiki

arXiv comment15 pages, 13 figures, ACL'2021

References in corpus (5)

• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs
• Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction