Neural document retrievers, including dense passage retrieval (DPR), have
outperformed classical lexical-matching retrievers, such as BM25, when
fine-tuned and tested on specific question-answering datasets. However, it has
been shown that the existing dense retrievers do not generalize well not only
out of domain but even in domain such as Wikipedia, especially when a named
entity in a question is a dominant clue for retrieval. In this paper, we
propose an approach toward in-domain generalization using the embeddings
generated by the frozen language model trained with the entities in the domain.
By not fine-tuning, we explore the possibility that the rich knowledge
contained in a pretrained language model can be used for retrieval tasks. The
proposed method outperforms conventional DPRs on entity-centric questions in
Wikipedia domain and achieves almost comparable performance to BM25 and
state-of-the-art SPAR model. We also show that the contextualized keys lead to
strong improvements compared to BM25 when the entity names consist of common
words. Our results demonstrate the feasibility of the zero-shot retrieval
method for entity-centric questions of Wikipedia domain, where DPR has
struggled to perform.

本文提出了一种基于预训练语言模型的检索方法，通过利用领域中已有的实体信息来实现领域内检索。实验结果表明，在如 Wikipedia 等领域中，本文提出的检索方法在实体相关问题上的效果要优于传统的 DPR 方法，并且可以在不进行微调的情况下有效利用预训练语言模型的知识资源，从而在实体名称包含常用词的情况下表现出比 BM25 更好的性能。