arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.04546cs.IR
收藏

CODEC:复杂文档和实体集合

CODEC: Complex Document and Entity Collection

Iain Mackie, Paul Owoicho, Carlos Gemmell, Sophie Fischer, Sean MacAvaney, Jeffrey Dalton

摘要:

CODEC是一个文档和实体排名基准,专注于复杂的研究主题。我们的目标是社会科学研究人员的论文式信息需求,即“英国的开放银行监管如何使挑战者银行受益?". CODEC包括研究人员开发的42个主题和一个新的重点网络语料库,其中包含实体链接的语义注释。该资源包括来自不同自动和交互式手动运行的17,509个文档和实体(每个主题416.9个)的专家判断。手动运行包括387个查询重写,为查询性能预测和自动重写评估提供数据。CODEC包括对最先进系统的分析,包括稠密检索和神经重新排序。结果表明,主题是具有挑战性的,为文档和实体排名的改进预留了空间。查询扩展与实体信息显示显着的收益在文档排序,展示了资源的价值,评估和改进面向实体的搜索。我们还表明,手动查询重构显着提高文档排序和实体排名的性能。总体而言,CODEC提供了具有挑战性的研究课题,以支持以实体为中心的搜索方法的开发和评估。

英文摘要:

CODEC is a document and entity ranking benchmark that focuses on complex research topics. We target essay-style information needs of social science researchers, i.e. "How has the UK's Open Banking Regulation benefited Challenger Banks?". CODEC includes 42 topics developed by researchers and a new focused web corpus with semantic annotations including entity links. This resource includes expert judgments on 17,509 documents and entities (416.9 per topic) from diverse automatic and interactive manual runs. The manual runs include 387 query reformulations, providing data for query performance prediction and automatic rewriting evaluation. CODEC includes analysis of state-of-the-art systems, including dense retrieval and neural re-ranking. The results show the topics are challenging with headroom for document and entity ranking improvement. Query expansion with entity information shows significant gains in document ranking, demonstrating the resource's value for evaluating and improving entity-oriented search. We also show that the manual query reformulations significantly improve document ranking and entity ranking performance. Overall, CODEC provides challenging research topics to support the development and evaluation of entity-centric search methods.

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。

↑