RA-NER: Retrieval augmented NER for knowledge intensive named entity recognition

Zhenwei DAI, Chen Luo, Zhen Li, Xianfeng Tang, Hanqing Lu, Rahul Goutam, Haiyang Zhang

Keywords: NER, retrieval augmented LLM, information retrieval

Abstract: NER (named entity recognition) model aims to recognize the named entities in the keywords. However, when the entities are extremely knowledge intensive, traditional NER model cannot encode all the knowledge in its parameters, thus fails to recognize those entities with high accuracy. In this paper, we propose retrieval-augmented NER model (RA-NER) to address this issue. RA-NER retrieves the most relevant information from an exhaustive external knowledge database to assist the entity recognition. We implement RA-NER for media related entity recognition task on an Amazon internal dataset, and achieve significant performance boost over the traditional deep-learning based NER model.

Submission Number: 98