arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04887cs.IR
收藏

基于嵌入的检索的相关性过滤

Relevance Filtering for Embedding-based Retrieval

Nicholas Rossi, Juexin Lin, Feng Liu, Zhen Yang, Tony Lee, Alessandro Magnani, Ciya Liao

AI总结:

针对 ANN 稠密检索缺乏天然截断且余弦分数难以解释的问题,提出 Cosine Adapter,用查询相关映射与全局阈值过滤不相关结果,显著提升精度并仅损失少量召回。

摘要:

在基于嵌入的检索中,近似最近邻(Approximate Nearest Neighbor,ANN)搜索能够从大规模数据集中高效检索相似物品。尽管最大化相关物品的召回率通常是检索系统的目标,但较低的精度可能导致糟糕的搜索体验。与词法检索通过关键词匹配固有地限制检索集大小不同,通过 ANN 搜索进行的稠密检索没有天然的截断点。此外,嵌入向量的余弦相似度分数通常通过对比损失或排序损失进行优化,这使其难以解释。因此,依赖 top-K 或余弦相似度截断往往不足以有效过滤不相关结果。这一问题在商品搜索中尤为突出,因为相关商品的数量通常很少。本文介绍了一种用于基于嵌入的检索的新型相关性过滤组件(名为“Cosine Adapter”),以应对这一挑战。我们的方法使用依赖于查询的映射函数,将原始余弦相似度分数映射为可解释的分数。随后,我们对映射后的分数应用全局阈值,以过滤不相关结果。我们能够显著提高检索集的精度,代价是损失少量召回率。我们的方法的有效性通过在公开 MS MARCO 数据集和 Walmart 内部商品搜索数据上的实验得到证明。此外,在 Walmart 网站上进行的在线 A/B 测试验证了该方法在真实电子商务场景中的实用价值。

英文摘要:

In embedding-based retrieval, Approximate Nearest Neighbor (ANN) search enables efficient retrieval of similar items from large-scale datasets. While maximizing recall of relevant items is usually the goal of retrieval systems, a low precision may lead to a poor search experience. Unlike lexical retrieval, which inherently limits the size of the retrieved set through keyword matching, dense retrieval via ANN search has no natural cutoff. Moreover, the cosine similarity scores of embedding vectors are often optimized via contrastive or ranking losses, which make them difficult to interpret. Consequently, relying on top-K or cosine-similarity cutoff is often insufficient to filter out irrelevant results effectively. This issue is prominent in product search, where the number of relevant products is often small. This paper introduces a novel relevance filtering component (called "Cosine Adapter") for embedding-based retrieval to address this challenge. Our approach maps raw cosine similarity scores to interpretable scores using a query-dependent mapping function. We then apply a global threshold on the mapped scores to filter out irrelevant results. We are able to significantly increase the precision of the retrieved set, at the expense of a small loss of recall. The effectiveness of our approach is demonstrated through experiments on both public MS MARCO dataset and internal Walmart product search data. Furthermore, online A/B testing on the Walmart site validates the practical value of our approach in real-world e-commerce settings.

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。

↑