From Contextual Search to Automatic Content Generation: Scaling Human Editorial Judgment

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


Duration: 1:15:52
165 views
2

Systems that present people with information inescapably make editorial judgments in determining what information to show and how to show it. However the editorial values used to make these determinations are generally invisible to users and in many cases even to the engineers who design them. This talk describes some of the problems that this creates, based mainly on an assessment of our own mistakes; and presents some technologies for providing explicit and visible editorial control in news and media information systems. I�ll also talk about our recent work on automatically generating stories from data based on human editorial judgment. A system based on this technology is already generating more than 10 thousand stories weekly in areas ranging from sports to business. This system is the nation�s most prolific and published author of, among other things, women�s collegiate softball stories. The stories compare favorably to those written by human beings.



Other Videos By Microsoft Research


2016-07-27Making money with �free� apps
2016-07-27Collecting a Heap of Shapes
2016-07-27Automatically Assessing Personality from Speech
2016-07-27Ten User Experience Best Practices for Windows Phone Application Development
2016-07-27Generalization Bounds and Consistency for Latent-Structural Probit and Ramp Loss
2016-07-27Structured Prediction in NLP: Dual Decomposition and Structured Sparsity
2016-07-27High Availability for Database Systems in Cloud Computing Environments
2016-07-27Batches: Unified and Efficient Access to RPC, WS, and SQL Services
2016-07-27Reliable Multithreading through Schedule Memoization
2016-07-27Generalized Oblivious Transfer (GOT)
2016-07-27From Contextual Search to Automatic Content Generation: Scaling Human Editorial Judgment
2016-07-27Bound Analysis of Imperative Programs with the Size-change Abstraction
2016-07-27A mobile context monitoring platform for dynamic mobile computing environments
2016-07-27Privacy Amplification and Non-Malleable Extractors Via Character Sums
2016-07-27Visualization Clusters: from Tiled Displays to Remote Visualization
2016-07-27The Median Hypothesis
2016-07-27Developing Natural Language-based Software Analyses & Tools to Expedite Software Maintenance
2016-07-27Semi-Supervised Learning for Acoustic and Prosodic Modeling in Speech Recognition
2016-07-27Code Bubbles: Making the Vision Real
2016-07-27A novel framework of effective resource management for multi-hop wireless networks
2016-07-27Trajectories and the Extended User Experience


Tags:
microsoft research