No
Yes
View More
View Less
Working...
Close
OK
Cancel
Confirm
System Message
Delete
My Schedule
An unknown error has occurred and your request could not be completed. Please contact support.
Scheduled
Scheduled
Wait Listed
Personal Calendar
Speaking
Conference Event
Meeting
Interest
There aren't any available sessions at this time.
Conflict Found
This session is already scheduled at another time. Would you like to...
Loading...
Please enter a maximum of {0} characters.
{0} remaining of {1} character maximum.
Please enter a maximum of {0} words.
{0} remaining of {1} word maximum.
must be 50 characters or less.
must be 40 characters or less.
Session Summary
We were unable to load the map image.
This has not yet been assigned to a map.
Search Catalog
Reply
Replies ()
Search
New Post
Microblog
Microblog Thread
Post Reply
Post
Your session timed out.
This web page is not optimized for viewing on a mobile device.Visit this site in a desktop browser or download the mobile app to access the full set of features.
2018 GTC San Jose
Favorite
Remove from My Interests

S81039 - Accelerating Machine Reading Comprehension Models Using GPUs

Session Speakers
Session Description

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.  


Additional Information
Speech and Language Processing
Cloud Services
Advanced technical
Talk
25 minutes
Session Schedule