E-commerce sellers are recommended keyphrases based on their inventory on which they advertise to increase buyer engagement (clicks/sales). Keyphrases must be pertinent to items; otherwise, it can result in seller dissatisfaction and poor targeting -- towards that end relevance filters are employed. In this work, we describe the shortcomings of training relevance filter models on biased click/sales signals. We re-conceptualize advertiser keyphrase relevance as interaction between two dynamical systems -- Advertising which produces the keyphrases and Search which acts as a middleman to reach buyers. We discuss the bias of search relevance systems (middleman bias) and the need to align advertiser keyphrases with search relevance signals. We also compare the performance of cross encoders and bi-encoders in modeling this alignment and the scalability of such a solution for sellers at eBay.

翻译：电子商务卖家根据其库存获得推荐的关键词，并基于这些关键词进行广告投放以提升买家参与度（点击/销售）。关键词必须与商品相关；否则可能导致卖家不满和低效的定向投放——为此需采用相关性过滤器。本研究阐述了基于有偏的点击/销售信号训练相关性过滤模型的缺陷。我们将广告主关键词相关性重新定义为两个动态系统间的交互：一是生成关键词的广告系统，二是作为中间商触达买家的搜索系统。我们探讨了搜索相关性系统存在的偏见（中间商偏见），以及将广告主关键词与搜索相关性信号对齐的必要性。此外，我们比较了交叉编码器与双向编码器在建模这种对齐关系时的性能表现，并分析了该解决方案在eBay平台卖家端的可扩展性。