Title:
SEMANTIC RELATION LEARNING DEVICE, SEMANTIC RELATION LEARNING METHOD, AND SEMANTIC RELATION LEARNING PROGRAM
Document Type and Number:
WIPO Patent Application WO/2020/144736
Kind Code:
A1
Abstract:
A semantic relation learning device (1) is provided with: a negative example data creation unit (12) that creates a plurality of negative example data pairs by combining language data items respectively constituting a plurality of positive example data pairs; a feature amount extraction unit (13) that extracts feature amounts from language data items respectively constituting the negative example data pairs; a similarity calculation unit (14) that calculates similarity between the feature amounts in the negative example data pairs; a learning negative example data creation unit (15) that, by classifying, on the basis of the similarity, the plurality of negative example data pairs into a plurality of predetermined similarity ranges, creates a plurality of learning negative example data sets respectively corresponding to the plurality of similarity ranges; a learning data set selection unit (17) that, in order following a selection schedule determined in advance on the basis of the plurality of similarity ranges, selects any one of the plurality of learning negative example data sets; and a learning processing unit (18) that performs a machine learning process by using the selected learning negative example data set and the plurality of positive example data pairs.
Inventors:
UCHIDE HAYATO (JP)
Application Number:
PCT/JP2019/000173
Publication Date:
July 16, 2020
Filing Date:
January 08, 2019
Export Citation:
Assignee:
MITSUBISHI ELECTRIC CORP (JP)
International Classes:
G06F16/00; G06F16/30
Domestic Patent References:
| WO2009123288A1 | 2009-10-08 |
Foreign References:
| JP2012243125A | 2012-12-10 | |||
| JP2018025956A | 2018-02-15 |
Attorney, Agent or Firm:
YAMAGATA Yoichi et al. (JP)
Download PDF: