arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.00229cs.IR
收藏

NIR-Prompt:一种多任务通用的神经信息检索训练框架

NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework

Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng

AI总结:

针对预训练语言模型在神经信息检索中泛化性差的问题,提出基于信号解耦的NIR-Prompt训练框架,通过双模块分别捕捉本质匹配信号与生成任务描述,在多类任务设置下提升了检索与重排序阶段的模型泛化能力。

摘要:

信息检索旨在从语料库中找出满足用户需求的信息。不同的需求对应不同的IR(信息检索)任务,例如文档检索、开放域问答、基于检索的对话等,而这些任务都采用相同的模式来评估文本之间的关联。这表明一个优秀的IR模型能够泛化到不同的任务和领域。然而,已有研究表明,当前最先进的神经信息检索(NIR)模型,例如预训练语言模型(PLMs),很难实现泛化,主要原因是端到端微调范式使得模型过度强调任务特定信号和领域偏差,却丧失了捕捉通用本质信号的能力。为解决这一问题,我们基于信号捕捉与信号组合解耦的思路,提出了一种适用于检索和重排序阶段的新型NIR训练框架,命名为NIR-Prompt。NIR-Prompt利用本质匹配模块(Essential Matching Module, EMM)捕捉本质匹配信号,并通过匹配描述模块(Matching Description Module, MDM)获取任务描述,该描述作为任务适配信息,用于组合本质匹配信号以适配不同任务。在域内多任务、域外多任务以及新任务适配三种设置下的实验表明,与基线模型相比,NIR-Prompt能够提升PLMs在NIR检索和重排序两个阶段的泛化能力。

英文摘要:

Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts. It indicates that a good IR model can generalize to different tasks and domains. However, previous studies indicate that state-of-the-art neural information retrieval (NIR) models, e.g, pre-trained language models (PLMs) are hard to generalize. Mainly because the end-to-end fine-tuning paradigm makes the model overemphasize task-specific signals and domain biases but loses the ability to capture generalized essential signals. To address this problem, we propose a novel NIR training framework named NIR-Prompt for retrieval and reranking stages based on the idea of decoupling signal capturing and combination. NIR-Prompt exploits Essential Matching Module (EMM) to capture the essential matching signals and gets the description of tasks by Matching Description Module (MDM). The description is used as task-adaptation information to combine the essential matching signals to adapt to different tasks. Experiments under in-domain multi-task, out-of-domain multi-task, and new task adaptation settings show that NIR-Prompt can improve the generalization of PLMs in NIR for both retrieval and reranking stages compared with 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。

↑