Tevatron：一个高效灵活的稠密检索工具包
Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval
摘要：
深度预训练语言模型的快速发展和大型数据集的引入推动了基于嵌入的稠密检索的研究。虽然已经出现了一些很好的研究论文，但其中许多都有自己的软件栈。这些堆栈通常针对某些特定的研究目标进行优化，而不是效率或代码结构。在本文中，我们提出了Tevatron，一个稠密检索工具包优化的效率，灵活性和代码的简单性。Tevatron为稠密检索提供了标准化的管道，包括文本处理、模型训练、语料库/查询编码和搜索。本文介绍了Tevatron的概述，并在几个IR和QA数据集上展示了其有效性和效率。我们还展示了Tevatron的灵活设计如何实现跨数据集、模型架构和加速器平台（GPU/TPU）的轻松泛化。我们相信Tevatron可以作为稠密检索系统研究的有效软件基础，包括设计，建模和优化。
英文摘要：
Recent rapid advancements in deep pre-trained language models and the introductions of large datasets have powered research in embedding-based dense retrieval. While several good research papers have emerged, many of them come with their own software stacks. These stacks are typically optimized for some particular research goals instead of efficiency or code structure. In this paper, we present Tevatron, a dense retrieval toolkit optimized for efficiency, flexibility, and code simplicity. Tevatron provides a standardized pipeline for dense retrieval including text processing, model training, corpus/query encoding, and search. This paper presents an overview of Tevatron and demonstrates its effectiveness and efficiency across several IR and QA data sets. We also show how Tevatron's flexible design enables easy generalization across datasets, model architectures, and accelerator platforms(GPU/TPU). We believe Tevatron can serve as an effective software foundation for dense retrieval system research including design, modeling, and optimization.
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。
