Tevatron: An Efficient and Flexible Toolkit for Neural Retrieval
Tevatron: An Efficient and Flexible Toolkit for Neural Retrieval
复制标题
DOI：
10.1145/3539618.3591805
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Luyu Gao
中科院分区：
文献类型：
--
作者：
Luyu Gao
最近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神经检索的研究。虽然已经出现了许多优秀的研究论文，但其中大多数都有自己的实现，这些实现通常是针对某些特定的研究目标而优化的，而不是效率或代码组织。在本文中，我们介绍了Tevatron，一个神经检索工具包，它针对效率，灵活性和代码简单性进行了优化。Tevatron能够对各种排名组件进行模型训练和评估，例如密集检索器，稀疏检索器和重新排序器。它还提供了一个标准化的管道，包括文本处理，模型训练，语料库/查询编码和搜索。此外，Tevatron还采用了经过充分研究的方法来提高检索器的有效性，例如硬负面挖掘和知识蒸馏。我们在本文中提供了Tevatron的概述，展示了其在多个IR和QA数据集上的有效性和效率。我们强调Tevatron的灵活设计，它可以轻松地跨数据集，模型架构和加速器平台（GPU和TPU）进行泛化。总的来说，我们相信Tevatron可以作为神经检索系统研究的坚实软件基础，包括它们的设计，建模和优化。
Recent rapid advances in deep pre-trained language models and the introduction of large datasets have powered research in embedding-based neural retrieval. While many excellent research papers have emerged, most of them come with their own implementations, which are typically optimized for some particular research goals instead of efficiency or code organization. In this paper, we introduce Tevatron, a neural retrieval toolkit that is optimized for efficiency, flexibility, and code simplicity. Tevatron enables model training and evaluation for a variety of ranking components such as dense retrievers, sparse retrievers, and rerankers. It also provides a standardized pipeline that includes text processing, model training, corpus/query encoding, and search. In addition, Tevatron incorporates well-studied methods for improving retriever effectiveness such as hard negative mining and knowledge distillation. We provide an overview of Tevatron in this paper, demonstrating its effectiveness and efficiency on multiple IR and QA datasets. We highlight Tevatron's flexible design, which enables easy generalization across datasets, model architectures, and accelerator platforms (GPUs and TPUs). Overall, we believe that Tevatron can serve as a solid software foundation for research on neural retrieval systems, including their design, modeling, and optimization.