AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
This solves the problem of organizing product information for online retail, enabling scalable knowledge graphs for search and question answering, though it appears incremental as it builds on existing KG methods.
The paper tackles the challenge of building a knowledge graph for all products in the world by developing AutoKnow, an automatic system that addresses issues like data sparsity and domain complexity, and it has been operational for over 11,000 product types.
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.