arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.09984cs.IRcs.CL
收藏

制作一个MIRACL:跨语言连续体的多语言信息检索

Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages

University of Waterloo(滑铁卢大学);University of Alberta(阿尔伯塔大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室)

Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin

摘要:

MIRACL(Multilingual信息检索Across a Continuum of Languages)是我们为WSDM 2023 Cup挑战赛构建的多语言数据集,专注于18种不同语言的临时检索,这些语言涵盖了全球超过30亿的母语使用者。这些语言有不同的类型,起源于许多不同的语系,并与不同数量的可用资源相关-包括研究人员通常描述为高资源和低资源的语言。我们的数据集旨在支持单语检索模型的创建和评估,其中查询和语料库使用相同的语言。总的来说,我们已经为这18种语言的维基百科上的大约77 k个查询收集了超过70万个高质量的相关性判断,所有评估都是由我们团队雇佣的母语人士进行的。我们的目标是促进研究,以提高跨语言的检索,从而提高世界各地不同人群的信息访问能力,特别是那些传统上服务不足的人群。本概述文件描述了我们与社区共享的数据集和基线。MIRACL的网站是在http://miracl.ai/。

英文摘要:

MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual dataset we have built for the WSDM 2023 Cup challenge that focuses on ad hoc retrieval across 18 different languages, which collectively encompass over three billion native speakers around the world. These languages have diverse typologies, originate from many different language families, and are associated with varying amounts of available resources -- including what researchers typically characterize as high-resource as well as low-resource languages. Our dataset is designed to support the creation and evaluation of models for monolingual retrieval, where the queries and the corpora are in the same language. In total, we have gathered over 700k high-quality relevance judgments for around 77k queries over Wikipedia in these 18 languages, where all assessments have been performed by native speakers hired by our team. Our goal is to spur research that will improve retrieval across a continuum of languages, thus enhancing information access capabilities for diverse populations around the world, particularly those that have been traditionally underserved. This overview paper describes the dataset and baselines that we share with the community. The MIRACL website is live at http://miracl.ai/.

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。

↑