Learning to Construct and Reason with a Large Knowledge Base of Extracted Information

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=KFwLcbttFR8


Duration: 1:08:28
285 views
2

Carnegie Mellon University's "Never Ending Language Learner" (NELL) has been running for over three years, and has automatically extracted from the web millions of facts concerning hundreds of thousands of entities and thousands of concepts. NELL works by coupling together many interrelated large-scale semi-supervised learning problems. In this talk I will discuss some of the technical problems we encountered in building NELL, and some of the issues involved in reasoning with this sort of large, diverse, and imperfect knowledge base. This is joint work with Tom Mitchell, Ni Lao, William Wang, and many other colleagues.



Other Videos By Microsoft Research


2016-07-26Art and Audience Participation: What Can We Expect from the Future?
2016-07-26Online News Sharing and Annotation in the Age of Participatory Media
2016-07-26Going Big on Big Data
2016-07-26Parallel Coordinates: Visual Multidimensional Geometry and its Applications
2016-07-26Microblogging During Small Scale Incidents
2016-07-26Patent Law's Perfect Storm
2016-07-26Multi-Party Computation: From Theory to Practice
2016-07-26Integrating Algorithmic and Behavioral Approaches to Crowdsourcing
2016-07-26Narrating with Networks: Making Sense of Event Log Data with Socio-Technical Trajectories
2016-07-26Algorithms and Perception for Interactive Free-Viewpoint Image-Based Navigation
2016-07-26Learning to Construct and Reason with a Large Knowledge Base of Extracted Information
2016-07-26Realtime Facial Animation
2016-07-26Learning Mixtures of Arbitrary Distributions over Large Discrete Domains
2016-07-26The Structural Theory of Pure Type Systems
2016-07-26Building Social Life Networks
2016-07-26How to write your next POPL paper in Dafny
2016-07-26Small Image Sensors and Big Visual Data
2016-07-26Why the Doorway is a Data Portal into Multi-Person Homes
2016-07-26Coordinating Software Development through Predictive Conflict Detection
2016-07-26Blur-Kernel Estimation from Spectral Irregularities
2016-07-26Quantum algorithms for Hamiltonian simulation


Tags:
microsoft research