CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion
This work addresses incomplete knowledge bases for AI applications, representing an incremental improvement over prior methods.
The paper tackled the problem of Knowledge Base Completion (KBC) by developing CEAR, a model that uses BERT with cross-entity attention to re-rank outputs from existing KBC models, achieving a new state-of-the-art on the OLPBench dataset.
Pre-trained language models (LMs) like BERT have shown to store factual knowledge about the world. This knowledge can be used to augment the information present in Knowledge Bases, which tend to be incomplete. However, prior attempts at using BERT for task of Knowledge Base Completion (KBC) resulted in performance worse than embedding based techniques that rely only on the graph structure. In this work we develop a novel model, Cross-Entity Aware Reranker (CEAR), that uses BERT to re-rank the output of existing KBC models with cross-entity attention. Unlike prior work that scores each entity independently, CEAR uses BERT to score the entities together, which is effective for exploiting its factual knowledge. CEAR achieves a new state of art for the OLPBench dataset.