arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.09313cs.IRcs.AIcs.CL
收藏

混合与协同段落重排序

Hybrid and Collaborative Passage Reranking

University of Science and Technology of China(中国科学技术大学);Huawei Cloud Computing Technologies Co., Ltd.(华为云计算技术有限公司)

Zongmeng Zhang, Wengang Zhou, Jiaxin Shi, Houqiang Li

AI总结:

针对段落检索中忽略上下文的问题,提出HybRank混合协同重排序方法,利用上游检索器相似度与稀疏/稠密特性,即插即用提升重排序性能。

摘要:

在段落检索系统中,初始的段落检索结果可能不尽如人意,这可以通过重排序方案来改进。现有的段落重排序解决方案侧重于增强查询与每个段落之间的交互,却忽略了初始检索列表中排名靠前的段落之间的上下文关系。为解决这一问题,我们提出了一种混合与协同段落重排序(HybRank)方法,该方法利用上游检索器的实质性相似度测量进行段落协同,并结合稀疏与稠密检索器的词汇与语义特性进行重排序。此外,基于现成的检索器特征,HybRank是一种即插即用的重排序器,能够增强任意段落列表,包括先前已重排序的列表。大量实验表明,HybRank在性能上相较于流行的检索与重排序方法有稳定提升,并验证了其核心组件的有效性。

英文摘要:

In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage separately, neglecting the context among the top-ranked passages in the initial retrieval list. To tackle this problem, we propose a Hybrid and Collaborative Passage Reranking (HybRank) method, which leverages the substantial similarity measurements of upstream retrievers for passage collaboration and incorporates the lexical and semantic properties of sparse and dense retrievers for reranking. Besides, built on off-the-shelf retriever features, HybRank is a plug-in reranker capable of enhancing arbitrary passage lists including previously reranked ones. Extensive experiments demonstrate the stable improvements of performance over prevalent retrieval and reranking methods, and verify the effectiveness of the core components of HybRank.

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。

↑