Dynamic Injection of Entity Knowledge into Dense Retrievers
Authors: Ikuya Yamada, Ryokan Ri, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
Abstract: Dense retrievers often struggle with queries involving less-frequent entities due to their limited entity knowledge. Knowledgeable Passage Retriever (KPR), a BERT-based retriever enhanced with a context-entity attention layer and dynamically updatable entity This design enables KPR to incorporate external entity knowledge without retraining. Experiments on three datasets show that KPR consistently improves retrieval accuracy, achieving a substantial 12.6% gain on the EntityQuestions dataset over the model without KPR extensions. When built on the off-the-shelf bge-base retriever, KPR achieves state-of-the-art performance among similarly sized models on two datasets.