论文标题
对零拍的详细检查彻底检查
A Thorough Examination on Zero-shot Dense Retrieval
论文作者
论文摘要
近年来，基于强大的预训练语言模型（PLM），近年来取得了重大检索（DR）的显着进步。 DR Models在几个基准数据集中取得了出色的性能，而在零摄像的检索设置中，它们的竞争不如传统的稀疏检索模型（例如BM25）那么具有竞争力。但是，在相关的文献中，仍然缺乏有关零击检索的详细且全面的研究。在本文中，我们介绍了对DR模型的零击功能的首次彻底检查。我们旨在确定关键因素并分析它们如何影响零射击检索性能。特别是，我们讨论了与源训练集有关的几个关键因素的效果，分析目标数据集的潜在偏见，并审查和比较现有的零摄像DR模型。我们的发现提供了重要的证据，以更好地理解和开发零照片的DR模型。
Recent years have witnessed the significant advance in dense retrieval (DR) based on powerful pre-trained language models (PLM). DR models have achieved excellent performance in several benchmark datasets, while they are shown to be not as competitive as traditional sparse retrieval models (e.g., BM25) in a zero-shot retrieval setting. However, in the related literature, there still lacks a detailed and comprehensive study on zero-shot retrieval. In this paper, we present the first thorough examination of the zero-shot capability of DR models. We aim to identify the key factors and analyze how they affect zero-shot retrieval performance. In particular, we discuss the effect of several key factors related to source training set, analyze the potential bias from the target dataset, and review and compare existing zero-shot DR models. Our findings provide important evidence to better understand and develop zero-shot DR models.
