Building Knowledgeable Machines
summary
Argues that large knowledge graphs materially improve AI decision making and shows concrete methods and results: a continuous reader NELL (running since 2010); domain schema induction via tensor factorization (60F) with 10x speedup and a TFBA extension for n-ary relations; entity canonicalization using embeddings and side information CESI canonicalization with ~15% boost; time‑stamping via graph convolution nets yielding ~18–19% absolute improvement; several published systems and open‑source code that actually improve benchmarks.
AI-written summary · about
chapters (31)
- 0:00Introduction
- 0:59Background Knowledge
- 4:25Laser
- 5:00Knowledge Graph
- 7:03Knowledge Panel
- 8:00NELL
- 10:15View of Knowledge
- 11:44Ontological Knowledge Graph
- 14:39Outline
- 14:57Problem
- 17:26tensor factorization
- 22:35Failed attempts
- 23:42Side informations
- 27:32Canonicalization
- 27:55Ceci
- 30:14Holy
- 30:35Side Information
- 31:01Objective
- 31:58Method
- 32:46Qualitative Examples
- 34:40Other Work
- 35:30Timestamping
- 36:14Model
- 36:35Deep Learning
- 39:01Knowledge Graphs
- 39:57Work spans
- 40:50Kinam
- 41:15Big Data and Dark Data
- 42:12Genome Insights Platform
- 42:58Track Crypto
- 44:00Contact Information
related talks
22mThe Nexus of Innovation: How Knowledge Graphs Fuel AI Scientific Breakthroughs
13mBuilding High-Performance AI Literature Processing
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
38mKnowledge Graphs : Adding a New Dimension to Vector Search and Generative AI
52mBuild Smarter Knowledge Management Systems with AI Technology
30mHow Graph Data Science Can Turbocharge Your Knowledge Graph
18mEvaluating the effectiveness of Deep Learning Models for Foundational Program Analysis(…)
21mLearning from History: The Past as a Compass for Systems Engineers in the Age of AI