GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Speech & Language Processing
Presentation
Media
Accelerating Machine Reading Comprehension Models Using GPUs
Abstract:
A common challenge for large-scale online services such as Microsoft Bing or Cortana is ensuring that queries complete fast.  Additionally, these services require support for new models to be created, tested and deployed in production at a very fast pace.  Come and learn some of the techniques we have used to deliver both.  Bing Search and Cortana adopt advanced Machine Reading Comprehension (MRC) models for answer extraction and identifying answer relevance. We will describe a number of innovations in the MRC models and also techniques for hardware acceleration at production scale.  
 
Topics:
Speech & Language Processing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S81039
Streaming:
Share: