Xian Li | AutoKnow: Self-Driving Knowledge Collection For Products
KGC 2021 Conference, Workshops and Tutorials
•
19m
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 a large number of categories, as well as large and constantly growing number of products. We present 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.
Up Next in KGC 2021 Conference, Workshops and Tutorials
-
Veronika Heimsbakk | Tales From The R...
When transforming amounts of plain text into semantic knowledge graphs using Resource Description Framework, a service for automatic interpretation became apparent. Manual interpretation of text depends on human domain knowledge and discovery of entities and relationships in the text. This proces...
-
Steven Gustafson | Connecting The Dot...
Knowledge graphs provide a way for us to capture and relate information into a representation that can mimic expert knowledge. One type of expert knowledge that has proven to be particularly useful in industry is reasoning by analogy, or using a replacement problem and solution pair to think abo...
-
Trey Botard | Bringing Time & Truth T...
Semantic systems provide tremendous opportunities to interoperate our data, facilitate shared vocabularies, and power enterprise knowledge graphs, but these increasingly distributed data ecosystems also introduce new instabilities and concerns. What happens when data we rely on is changing in une...
