arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.02073cs.IR
收藏

理解用于文本检索的差分搜索索引

Understanding Differential Search Index for Text Retrieval

Xiaoyang Chen, Yanjiang Liu, Ben He, Le Sun, Yingfei Sun

AI总结:

本研究分析了差分搜索索引(DSI)在排他性、完整性和相关性排序方面的基本索引与检索能力,发现其区分相关文档的能力不足,并提出一种多任务蒸馏方法在不改变模型结构的前提下有效提升了检索质量。

摘要:

差分搜索索引(DSI)是一种新颖的信息检索(IR)框架,它利用可微函数针对给定查询生成排序后的文档标识符列表。然而,由于端到端神经架构的黑盒性质,DSI在多大程度上具备基本的索引和检索能力仍有待理解。为了弥补这一差距,在本研究中,我们定义并考察了一个正常运作的IR框架应具备的三项重要能力,即排他性、完整性和相关性排序。我们的分析实验表明,尽管DSI在记忆从伪查询到文档标识符的单向映射方面表现出色,但它在区分相关文档与随机文档方面存在不足,从而对其检索效果产生了负面影响。为了解决这个问题,我们提出了一种多任务蒸馏方法,在不改变模型结构的情况下提升检索质量,并成功赋予其改善的索引能力。通过在多个数据集上进行的实验,我们证明我们提出的方法优于先前的DSI基线。

英文摘要:

The Differentiable Search Index (DSI) is a novel information retrieval (IR) framework that utilizes a differentiable function to generate a sorted list of document identifiers in response to a given query. However, due to the black-box nature of the end-to-end neural architecture, it remains to be understood to what extent DSI possesses the basic indexing and retrieval abilities. To mitigate this gap, in this study, we define and examine three important abilities that a functioning IR framework should possess, namely, exclusivity, completeness, and relevance ordering. Our analytical experimentation shows that while DSI demonstrates proficiency in memorizing the unidirectional mapping from pseudo queries to document identifiers, it falls short in distinguishing relevant documents from random ones, thereby negatively impacting its retrieval effectiveness. To address this issue, we propose a multi-task distillation approach to enhance the retrieval quality without altering the structure of the model and successfully endow it with improved indexing abilities. Through experiments conducted on various datasets, we demonstrate that our proposed method outperforms previous DSI baselines.

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。

↑