arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03411cs.CLcs.AIcs.IR
收藏

先生成后检索:商品搜索中的意图感知 FAQ 检索

Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search

Amazon.com, Inc.(亚马逊公司)

Zhiyu Chen, Jason Choi, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

AI总结:

针对商品搜索中的信息寻求查询,提出由意图分类器和查询改写模型组成的意图感知 FAQ 检索系统,显著提升准确率、降低延迟并获得用户正向反馈。

摘要:

与商品搜索引擎交互的顾客正越来越多地提出信息寻求型查询。常见问题(FAQ)检索旨在为具有问题意图的用户查询检索常见的问答对。将 FAQ 检索集成到商品搜索中,不仅能够帮助用户做出更明智的购买决策,还可以通过高效的售后支持提升用户留存。如何在不干扰用户购物体验的情况下,判断某条 FAQ 条目何时能够满足用户在商品搜索中的信息需求,是一项重要挑战。我们提出了一种意图感知的 FAQ 检索系统,该系统由两部分组成:(1)一个意图分类器,用于预测用户的信息需求何时可以由 FAQ 回答;(2)一个改写模型,用于将查询重写为自然语言问题。离线评估表明,与基线系统相比,我们的方法在检索真实 FAQ 时将 Hit@1 提高了 13%,同时将延迟降低了 95%。这些改进进一步得到了真实用户反馈的验证:在商品搜索结果顶部展示的 FAQ 中,有 71% 获得了明确的正向用户反馈。总体而言,我们的研究结果为大规模将 FAQ 检索集成到商品搜索中展示了有前景的方向。

英文摘要:

Customers interacting with product search engines are increasingly formulating information-seeking queries. Frequently Asked Question (FAQ) retrieval aims to retrieve common question-answer pairs for a user query with question intent. Integrating FAQ retrieval in product search can not only empower users to make more informed purchase decisions, but also enhance user retention through efficient post-purchase support. Determining when an FAQ entry can satisfy a user's information need within product search, without disrupting their shopping experience, represents an important challenge. We propose an intent-aware FAQ retrieval system consisting of (1) an intent classifier that predicts when a user's information need can be answered by an FAQ; (2) a reformulation model that rewrites a query into a natural question. Offline evaluation demonstrates that our approach improves Hit@1 by 13% on retrieving ground-truth FAQs, while reducing latency by 95% compared to baseline systems. These improvements are further validated by real user feedback, where 71% of displayed FAQs on top of product search results received explicit positive user feedback. Overall, our findings show promising directions for integrating FAQ retrieval into product search at scale.

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。

↑