AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
Abstract
Can one build a knowledge graph (KG) for all products in the world? Knowledge graphs have firmly established themselves as valuable sources of information for search and question answering, and it is natural to wonder if a KG can contain information about products offered at online retail sites. There have been several successful examples of generic KGs, but organizing information about products poses many additional challenges, including sparsity and noise of structured data for products, complexity of the domain with millions of product types and thousands of attributes, heterogeneity across large number of categories, as well as large and constantly growing number of products. We describe AutoKnow, our automatic (self-driving) system that addresses these challenges. The system includes a suite of novel techniques for taxonomy construction, product property identification, knowledge extraction, anomaly detection, and synonym discovery. AutoKnow is (a) automatic, requiring little human intervention, (b) multi-scalable, scalable in multiple dimensions (many domains, many products, and many attributes), and (c) integrative, exploiting rich customer behavior logs. AutoKnow has been operational in collecting product knowledge for over 11K product types.
Keywords
Cite
@article{arxiv.2006.13473,
title = {AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types},
author = {Xin Luna Dong and Xiang He and Andrey Kan and Xian Li and Yan Liang and Jun Ma and Yifan Ethan Xu and Chenwei Zhang and Tong Zhao and Gabriel Blanco Saldana and Saurabh Deshpande and Alexandre Michetti Manduca and Jay Ren and Surender Pal Singh and Fan Xiao and Haw-Shiuan Chang and Giannis Karamanolakis and Yuning Mao and Yaqing Wang and Christos Faloutsos and Andrew McCallum and Jiawei Han},
journal= {arXiv preprint arXiv:2006.13473},
year = {2020}
}
Comments
KDD 2020