Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
This work addresses the limitations of existing embedding-based and text-based methods for knowledge graph completion, offering a novel approach that enhances accuracy for tasks involving incomplete triples.
The paper tackles the problem of knowledge graph completion by proposing KGR3, a context-enriched framework that integrates retrieval, reasoning, and re-ranking modules, achieving absolute Hits@1 improvements of 12.3% and 5.6% on FB15k237 and WN18RR datasets.
The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle with the semantic gap between KG triples and natural language. Apart from triples, entity contexts (e.g., labels, descriptions, aliases) also play a significant role in augmenting KGs. To address these limitations, we propose KGR3, a context-enriched framework for KGC. KGR3 is composed of three modules. Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity. Then, the Reasoning module employs a large language model to generate potential answers for each query triple. Finally, the Re-ranking module combines candidate answers from the two modules mentioned above, and fine-tunes an LLM to provide the best answer. Extensive experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods. Specifically, the best variant of KGR3 achieves absolute Hits@1 improvements of 12.3% and 5.6% on the FB15k237 and WN18RR datasets.