Learning a Product Relevance Model from Click-Through Data in E-Commerce

被引:22
作者
Yao, Shaowei [1 ]
Tan, Jiwei [2 ]
Chen, Xi [2 ]
Yang, Keping [2 ]
Xiao, Rong [2 ]
Deng, Hongbo [2 ]
Wan, Xiaojun [1 ]
机构
[1] Peking Univ, Beijing, Peoples R China
[2] Alibaba Grp, Hangzhou, Peoples R China
来源
PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021) | 2021年
关键词
neural networks; e-commerce; semantic matching;
D O I
10.1145/3442381.3450129
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The search engine plays a fundamental role in online e-commerce systems, to help users find the products they want from the massive product collections. Relevance is an essential requirement for e-commerce search, since showing products that do not match search query intent will degrade user experience. With the existence of vocabulary gap between user language of queries and seller language of products, measuring semantic relevance is necessary and neural networks are engaged to address this task. However, semantic relevance is different from click-through rate prediction in that no direct training signal is available. Most previous attempts learn relevance models from user click-through data that are cheap and abundant. Unfortunately, click behavior is noisy and misleading, which is affected by not only relevance but also factors including price, image and attractive titles. Therefore, it is challenging but valuable to learn relevance models from click-through data. In this paper, we propose a new relevance learning framework that concentrates on how to train a relevance model from the weak supervision of click-through data. Different from previous efforts that treat samples as either relevant or irrelevant, we construct more fine-grained samples for training. We propose a novel way to consider samples of different relevance confidence, and come up with a new training objective to learn a robust relevance model with desirable score distribution. The proposed model is evaluated on offline annotated data and online A/B testing, and it achieves both promising performance and high computational efficiency. The model has already been deployed online, serving the search traffic of Taobao for over a year.
引用
收藏
页码:2890 / 2899
页数:10
相关论文
共 28 条
[1]  
[Anonymous], 2014, ARXIV14126629
[2]   Why Do People Buy Seemingly Irrelevant Items in Voice Product Search? [J].
Carmel, David ;
Haramaty, Elad ;
Lazerson, Arnon ;
Lewin-Eytan, Liane ;
Maarek, Yoelle .
PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM '20), 2020, :79-87
[3]   Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search [J].
Dai, Zhuyun ;
Xiong, Chenyan ;
Callan, Jamie ;
Liu, Zhiyuan .
WSDM'18: PROCEEDINGS OF THE ELEVENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2018, :126-134
[4]  
Davis J., 2006, P 23 INT C MACH LEAR, P233, DOI [10.1145/1143844.1143874, DOI 10.1145/1143844.1143874]
[5]   Neural Ranking Models with Weak Supervision [J].
Dehghani, Mostafa ;
Zamani, Hamed ;
Severyn, Aliaksei ;
Kamps, Jaap ;
Croft, W. Bruce .
SIGIR'17: PROCEEDINGS OF THE 40TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2017, :65-74
[6]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171
[7]   A Deep Relevance Matching Model for Ad-hoc Retrieval [J].
Guo, Jiafeng ;
Fan, Yixing ;
Ai, Qingyao ;
Croft, W. Bruce .
CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2016, :55-64
[8]  
Hu BT, 2014, ADV NEUR IN, V27
[9]  
Huang PS, 2013, PROCEEDINGS OF THE 22ND ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM'13), P2333
[10]   A unified Neural Network Approach to E-Commerce Relevance Learning [J].
Jiang, Yunjiang ;
Shang, Yue ;
Li, Rui ;
Yang, Wen-Yun ;
Tang, Guoyu ;
Ma, Chaoyi ;
Xiao, Yun ;
Zhao, Eric .
1ST INTERNATIONAL WORKSHOP ON DEEP LEARNING PRACTICE FOR HIGH-DIMENSIONAL SPARSE DATA WITH KDD (DLP-KDD 2019), 2019,