当前位置: X-MOL 学术arXiv.cs.IR › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Ranker-agnostic Contextual Position Bias Estimation
arXiv - CS - Information Retrieval Pub Date : 2021-07-28 , DOI: arxiv-2107.13327
Oriol Barbany Mayor, Vito Bellini, Alexander Buchholz, Giuseppe Di Benedetto, Diego Marco Granziol, Matteo Ruffini, Yannik Stein

Learning-to-rank (LTR) algorithms are ubiquitous and necessary to explore the extensive catalogs of media providers. To avoid the user examining all the results, its preferences are used to provide a subset of relatively small size. The user preferences can be inferred from the interactions with the presented content if explicit ratings are unavailable. However, directly using implicit feedback can lead to learning wrong relevance models and is known as biased LTR. The mismatch between implicit feedback and true relevances is due to various nuisances, with position bias one of the most relevant. Position bias models consider that the lack of interaction with a presented item is not only attributed to the item being irrelevant but because the item was not examined. This paper introduces a method for modeling the probability of an item being seen in different contexts, e.g., for different users, with a single estimator. Our suggested method, denoted as contextual (EM)-based regression, is ranker-agnostic and able to correctly learn the latent examination probabilities while only using implicit feedback. Our empirical results indicate that the method introduced in this paper outperforms other existing position bias estimators in terms of relative error when the examination probability varies across queries. Moreover, the estimated values provide a ranking performance boost when used to debias the implicit ranking data even if there is no context dependency on the examination probabilities.

中文翻译:

Ranker-agnostic Contextual Position Bias Estimation

学习排名 (LTR) 算法无处不在,对于探索媒体提供商的广泛目录是必不可少的。为避免用户检查所有结果,其首选项用于提供相对较小尺寸的子集。如果显式评级不可用,则可以从与所呈现内容的交互中推断出用户偏好。然而,直接使用隐式反馈会导致学习错误的相关模型,这被称为有偏差的 LTR。隐式反馈和真实相关性之间的不匹配是由于各种麻烦造成的,位置偏差是最相关的一种。位置偏差模型认为,与呈现的项目缺乏交互不仅归因于该项目不相关,还因为该项目未经过检查。本文介绍了一种使用单个估计器对在不同上下文(例如,对于不同用户)中看到的项目的概率进行建模的方法。我们建议的方法,表示为基于上下文 (EM) 的回归,是排名不可知的,并且能够在仅使用隐式反馈的同时正确学习潜在的检查概率。我们的实证结果表明,当检查概率因查询而异时,本文中介绍的方法在相对误差方面优于其他现有的位置偏差估计器。此外,当用于消除隐式排名数据的偏差时,即使不存在对检查概率的上下文依赖性,估计值也会提供排名性能提升。表示为基于上下文 (EM) 的回归,是排名不可知的,并且能够在仅使用隐式反馈的同时正确学习潜在的检查概率。我们的实证结果表明,当检查概率因查询而异时,本文中介绍的方法在相对误差方面优于其他现有的位置偏差估计器。此外,当用于消除隐式排名数据的偏差时,即使不存在对检查概率的上下文依赖性,估计值也会提供排名性能提升。表示为基于上下文 (EM) 的回归,是排名不可知的,并且能够在仅使用隐式反馈的同时正确学习潜在的检查概率。我们的实证结果表明,当检查概率因查询而异时,本文中介绍的方法在相对误差方面优于其他现有的位置偏差估计器。此外,当用于消除隐式排名数据的偏差时,即使不存在对检查概率的上下文依赖性,估计值也会提供排名性能提升。我们的实证结果表明,当检查概率因查询而异时,本文中介绍的方法在相对误差方面优于其他现有的位置偏差估计器。此外,当用于消除隐式排名数据的偏差时,即使不存在对检查概率的上下文依赖性,估计值也会提供排名性能提升。我们的实证结果表明,当检查概率因查询而异时,本文中介绍的方法在相对误差方面优于其他现有的位置偏差估计器。此外,当用于消除隐式排名数据的偏差时,即使不存在对检查概率的上下文依赖性,估计值也会提供排名性能提升。
更新日期:2021-07-29
down
wechat
bug