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 2307.02740cs.IRcs.CL
收藏

利用目标域描述的稠密检索自适应

Dense Retrieval Adaptation using Target Domain Description

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Bloomberg(彭博社)

Helia Hashemi, Yong Zhuang, Sachith Sri Ram Kothur, Srivas Prasad, Edgar Meij, W. Bruce Croft

AI总结:

本文提出一种新的信息检索领域自适应设定:仅利用目标域文本描述自动构建合成数据,并据此适配稠密检索模型,在多个目标领域上验证了其有效性。

摘要:

在信息检索(IR)中,领域自适应是指将检索模型适配到一个数据分布与源域不同的新领域的过程。该领域的现有方法主要关注无监督领域自适应,即可以访问目标文档集合;或监督(通常是少样本)领域自适应,即还可以访问目标域中(有限的)标注数据。此外,也有研究致力于在不进行任何自适应的情况下提升检索模型的零样本性能。本文提出了信息检索中一个尚未被探索的新领域自适应类别。在此设定下,与零样本场景类似,我们假设检索模型无法访问目标文档集合;但与之不同的是,模型可以访问一段简要的文本描述,用以说明目标领域。我们定义了检索任务中的领域属性分类体系,以理解源域中可以被适配到目标域的不同性质。我们提出了一种新颖的自动数据构建流水线,在给定文本领域描述的情况下,生成合成文档集合、查询集和伪相关性标签。在五个不同目标领域上的大量实验表明,利用所构建的合成数据对稠密检索模型进行自适应,能够在目标领域上取得有效的检索性能。

英文摘要:

In information retrieval (IR), domain adaptation is the process of adapting a retrieval model to a new domain whose data distribution is different from the source domain. Existing methods in this area focus on unsupervised domain adaptation where they have access to the target document collection or supervised (often few-shot) domain adaptation where they additionally have access to (limited) labeled data in the target domain. There also exists research on improving zero-shot performance of retrieval models with no adaptation. This paper introduces a new category of domain adaptation in IR that is as-yet unexplored. Here, similar to the zero-shot setting, we assume the retrieval model does not have access to the target document collection. In contrast, it does have access to a brief textual description that explains the target domain. We define a taxonomy of domain attributes in retrieval tasks to understand different properties of a source domain that can be adapted to a target domain. We introduce a novel automatic data construction pipeline that produces a synthetic document collection, query set, and pseudo relevance labels, given a textual domain description. Extensive experiments on five diverse target domains show that adapting dense retrieval models using the constructed synthetic data leads to effective retrieval performance on the target domain.

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。

↑