arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.18005cs.IR
收藏

信息检索中的负采样技术:综述

Negative Sampling Techniques in Information Retrieval: A Survey

University of Innsbruck(因斯布鲁克大学)

Laurin Wischounig, Abdelrahman Abdallah, Adam Jatowt

AI总结:

本文综述了密集信息检索中负采样技术,探讨了随机、静态/动态挖掘及合成数据集等方法,并分析了效果、计算成本和实现难度之间的权衡。

摘要:

信息检索(IR)是许多现代自然语言处理(NLP)应用的基础。密集检索(DR)的兴起,利用神经网络学习语义向量表示,显著提升了IR性能。通过对比学习训练有效密集检索器的核心是选择有信息量的负样本。本文综述合成35篇开创性论文,提供了一个全面且最新的密集IR负采样技术概述。我们的独特贡献是专注于现代NLP应用,并包含最近由大型语言模型(LLM)驱动的方法,这是先前综述中缺失的领域。我们提出了一种分类法,将包括随机、静态/动态挖掘以及合成数据集等技术进行分类。然后分析这些方法在效果、计算成本和实现难度之间的权衡。综述最后概述了当前挑战和LLM生成合成数据的未来发展方向。

英文摘要:

Information Retrieval (IR) is fundamental to many modern NLP applications. The rise of dense retrieval (DR), using neural networks to learn semantic vector representations, has significantly advanced IR performance. Central to training effective dense retrievers through contrastive learning is the selection of informative negative samples. Synthesizing 35 seminal papers, this survey provides a comprehensive and up-to-date overview of negative sampling techniques in dense IR. Our unique contribution is the focus on modern NLP applications and the inclusion of recent Large Language Model (LLM)-driven methods, an area absent in prior reviews. We propose a taxonomy that categorizes techniques including random, static/dynamically mined, and synthetic datasets. We then analyze these approaches with respect to trade-offs between effectiveness, computational cost, and implementation difficulty. The survey concludes by outlining current challenges and promising future directions for the use of LLM-generated synthetic data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑