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 2108.08787cs.CLcs.IR
收藏

Mr. TyDi:一个多语言的稠密检索基准

Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval

University of Waterloo(滑铁卢大学)

Xinyu Zhang, Xueguang Ma, Peng Shi, Jimmy Lin

摘要:

我们提出了先生TyDi,一个多语言的基准数据集,用于在11种类型学上不同的语言中进行单语言检索,旨在评估学习密集表示的排名。该资源的目标是刺激非英语语言中稠密检索技术的研究,其动机是最近观察到现有的表示学习技术在应用于分布外数据时表现不佳。作为一个起点,我们为这个新的数据集提供了zero-shot基线,这是基于我们称之为“mDPR”的DPR的多语言适应。实验表明,尽管mDPR的有效性远低于BM 25,但密集表示似乎仍然提供了有价值的相关性信号,改进BM 25导致稀疏-密集混合。除了分析我们的结果,我们还讨论了未来的挑战,并提出了多语言稠密检索的研究议程。TyDi先生可在https://github.com/castorini/mr.tydi下载。

英文摘要:

We present Mr. TyDi, a multi-lingual benchmark dataset for mono-lingual retrieval in eleven typologically diverse languages, designed to evaluate ranking with learned dense representations. The goal of this resource is to spur research in dense retrieval techniques in non-English languages, motivated by recent observations that existing techniques for representation learning perform poorly when applied to out-of-distribution data. As a starting point, we provide zero-shot baselines for this new dataset based on a multi-lingual adaptation of DPR that we call "mDPR". Experiments show that although the effectiveness of mDPR is much lower than BM25, dense representations nevertheless appear to provide valuable relevance signals, improving BM25 results in sparse-dense hybrids. In addition to analyses of our results, we also discuss future challenges and present a research agenda in multi-lingual dense retrieval. Mr. TyDi can be downloaded at https://github.com/castorini/mr.tydi.

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。

↑