期刊
ACM TRANSACTIONS ON INFORMATION SYSTEMS
卷 40, 期 4, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3486250
关键词
Semantic retrieval models; information retrieval; survey
资金
- Beijing Academy of Artificial Intelligence (BAAI) [BAAI2019ZD0306]
- National Natural Science Foundation of China (NSFC) [61902381, 62006218, 61872338]
- Youth Innovation Promotion Association CAS [20144310, 2021100]
- Lenovo-CAS Joint Lab Youth Scientist Project
- Foundation and Frontier Research Key Program of Chongqing Science and Technology Commission [cstc2017jcyjBX0059]
This article introduces the practical solution of multi-stage ranking pipelines in modern search systems. The focus is on the first-stage retrieval models, where researchers aim to build semantic models to achieve high recall efficiently. The article discusses the current landscape, challenges, and future directions in this field.
Multi-stage ranking pipelines have been a practical solution in modern search systems, where the first-stage retrieval is to return a subset of candidate documents and latter stages attempt to re-rank those candidates. Unlike re-ranking stages going through quick technique shifts over the past decades, the first-stage retrieval has long been dominated by classical term-based models. Unfortunately, these models suffer from the vocabulary mismatch problem, which may block re-ranking stages from relevant documents at the very beginning. Therefore, it has been a long-term desire to build semantic models for the first-stage retrieval that can achieve high recall efficiently. Recently, we have witnessed an explosive growth of research interests on the first-stage semantic retrieval models. We believe it is the right time to survey current status, learn from existing methods, and gain some insights for future development. In this article, we describe the current landscape of the first-stage retrieval models under a unified framework to clarify the connection between classical term-based retrieval methods, early semantic retrieval methods, and neural semantic retrieval methods. Moreover, we identify some open challenges and envision some future directions, with the hope of inspiring more research on these important yet less investigated topics.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据