Title:
MIXED PROPOSAL BASED MODEL TRAINING SYSTEM
Document Type and Number:
WIPO Patent Application WO/2016/179755
Kind Code:
A1
Abstract:
Each token for containing an element in the training data is sampled according to a factorization strategy in training. Instead of using a single proposal, the property value of the target element located at the token being scanned is iteratively updated one or more times based on a combination of an element proposal and a context proposal. The element proposal tends to accept a value that is popular for the target element independently of the current piece of data, while the context proposal tends to accept whenever the property value that is popular in the context of the target data or popular for the element itself. The proposed modeling training approach can converge in a quite efficient way.
Inventors:
YUAN JINHUI (CN)
LIU TIE-YAN (CN)
LIU TIE-YAN (CN)
Application Number:
PCT/CN2015/078592
Publication Date:
November 17, 2016
Filing Date:
May 08, 2015
Export Citation:
Assignee:
MICROSOFT TECHNOLOGY LICENSING LLC (US)
YUAN JINHUI (CN)
YUAN JINHUI (CN)
International Classes:
G06F17/30; G06N20/00
Foreign References:
| CN101354714A | 2009-01-28 | |||
| CN103116588A | 2013-05-22 | |||
| CN103207899A | 2013-07-17 | |||
| US20100332503A1 | 2010-12-30 |
Attorney, Agent or Firm:
KING & WOOD MALLESONS (East Tower World Financial Centre,, No.1 Dongsanhuan Zhonglu, Chaoyang District, Beijing 0, CN)
Download PDF: