arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.00937cs.IRcs.CL
收藏

语义产品搜索

Semantic Product Search

Amazon(亚马逊公司);Carnegie Mellon University(卡内基梅隆大学)

Priyanka Nigam, Yiwei Song, Vijai Mohan, Vihan Lakshman, Weitian, Ding, Ankit Shingavi, Choon Hui Teo, Hao Gu, Bing Yin

摘要:

我们研究产品搜索中的语义匹配问题,即给定一个客户查询,从目录中检索所有语义相关的产品。通过倒排索引进行的纯词汇匹配在这方面是不够的,这是由于以下几个因素:a)缺乏对上位词、同义词和反义词的理解,b)对形态变体的脆弱性(例如“woman”与“women”),以及c)对拼写错误的敏感性。为了解决这些问题,我们训练了一个使用客户行为数据进行语义匹配的深度学习模型。最近,大部分关于使用深度学习的大规模语义搜索的工作都集中在网络搜索的排名上。相比之下,产品搜索的语义匹配提出了一些新的挑战,我们在本文中阐述。我们通过a)开发一个新的损失函数来解决这些挑战,该函数具有一个内置的阈值来区分随机的负面示例、印象深刻但未购买的示例和正面示例(购买的物品),b)使用平均池结合n元语法来捕获短程语言模式,c)使用散列来处理词汇表标记,以及d)使用模型并行训练架构来跨8个GPU扩展。我们提出了令人信服的离线结果,证明与使用相同标记化方法的基线最先进的语义搜索方法相比,Recall@100至少提高了4.7%,平均平均精度(MAP)提高了14.5%。此外,我们提出的结果,并讨论学习从在线A/B测试,证明了我们的方法的有效性。

英文摘要:

We study the problem of semantic matching in product search, that is, given a customer query, retrieve all semantically related products from the catalog. Pure lexical matching via an inverted index falls short in this respect due to several factors: a) lack of understanding of hypernyms, synonyms, and antonyms, b) fragility to morphological variants (e.g. "woman" vs. "women"), and c) sensitivity to spelling errors. To address these issues, we train a deep learning model for semantic matching using customer behavior data. Much of the recent work on large-scale semantic search using deep learning focuses on ranking for web search. In contrast, semantic matching for product search presents several novel challenges, which we elucidate in this paper. We address these challenges by a) developing a new loss function that has an inbuilt threshold to differentiate between random negative examples, impressed but not purchased examples, and positive examples (purchased items), b) using average pooling in conjunction with n-grams to capture short-range linguistic patterns, c) using hashing to handle out of vocabulary tokens, and d) using a model parallel training architecture to scale across 8 GPUs. We present compelling offline results that demonstrate at least 4.7% improvement in Recall@100 and 14.5% improvement in mean average precision (MAP) over baseline state-of-the-art semantic search methods using the same tokenization method. Moreover, we present results and discuss learnings from online A/B tests which demonstrate the efficacy of our method.

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。

↑