Building an Autonomous Knowledge Graph with Mike Tung

800 800 The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Today we’re joined by Mike Tung, Founder, and CEO of Diffbot.

At Diffbot, Mike and his team have built a few tools, with our main focus today being their knowledge graph. Inspired by Fei Fei Li’s Imagenet, Mike set out with the goal of “building an Imagenet for language or general concepts.” After a few years of, as he describes it, “sitting in a dark basement, working on the math problems,” Mike had developed the Diffbot knowledge graph, which is the “only one that is fully built by an autonomous system.” In our conversation, we discuss how their knowledge graph differs from more mainstream use cases like Google Search and MSFT Bing, including a quick history lesson/behind the scenes of how Google search was built, and how it’s different from Diffbot’s knowledge graph. We also discuss the developer experience with the knowledge graph and other tools, like Extraction API and Crawlbot, and challenges like knowledge fusion.

About Mike

Mentioned in the Interview

  • Diffbot on Github
  • Paper: KnowledgeNet: A Benchmark Dataset for Knowledge Base Population
  • EMNLP Conference
  • ImageNet
  • Check it out

    “More On That Later” by Lee Rosevere licensed under CC By 4.0

    Leave a Reply

    Your email address will not be published.