arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.06136cs.IR
收藏

数据驱动的排序相关性判断

Data-Driven Relevance Judgments for Ranking Evaluation

Nuno Moniz, Luís Torgo, João Vinagre

摘要:

在信息检索中,排序评估度量是设计和改进工作的基本要素。我们观察到,大多数流行的指标忽略了用于获得排名的分数中描述的信息。这可能会造成一个数字缩放问题,导致根据排名项目得分之间的差异程度对评价进行低估或高估。这项工作的目的是提出一个原则性的方式量化多等级的相关性判断的项目,使更准确的处罚排序错误的排名。我们提出了一个数据驱动的生成相关性函数的基础上的一组项目的分数和它的应用程序之间的分歧程度的评价指标归一化贴现累积增益(nDCG)。我们使用合成数据来证明我们的建议的兴趣,并结合来自Google News的新闻项目的数据及其在Twitter中的受欢迎程度,以显示其与标准nDCG相比的性能。结果表明,与标准nDCG相比,我们的提案能够提供更细粒度的排名评估,并且后者经常根据项目得分的差异低估或高估其评估得分。

英文摘要:

Ranking evaluation metrics are a fundamental element of design and improvement efforts in information retrieval. We observe that most popular metrics disregard information portrayed in the scores used to derive rankings, when available. This may pose a numerical scaling problem, causing an under- or over-estimation of the evaluation depending on the degree of divergence between the scores of ranked items. The purpose of this work is to propose a principled way of quantifying multi-graded relevance judgments of items and enable a more accurate penalization of ordering errors in rankings. We propose a data-driven generation of relevance functions based on the degree of the divergence amongst a set of items' scores and its application in the evaluation metric Normalized Discounted Cumulative Gain (nDCG). We use synthetic data to demonstrate the interest of our proposal and a combination of data on news items from Google News and their respective popularity in Twitter to show its performance in comparison to the standard nDCG. Results show that our proposal is capable of providing a more fine-grained evaluation of rankings when compared to the standard nDCG, and that the latter frequently under- or over-estimates its evaluation scores in light of the divergence of items' scores.

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。

↑