Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.

翻译：高效准确的产品相关性评估对于用户体验和商业成功至关重要。训练高质量的相关性评估模型需要高质量的查询-产品对，这通常通过负采样策略实现。然而，当前方法因误采样假阴性样本而引入池化偏差，导致性能下降和商业影响受损。为解决此问题，我们提出了一种新型负采样策略——偏差缓解硬负采样（BHNS），该策略基于我们原创的假阴性估计算法，专门用于识别和修正假阴性样本。在Instacart搜索场景中的实验证实，BHNS对实际电商应用具有有效性。此外，在公开数据集上的对比分析展示了其适用于多样化应用的跨领域潜力。