Non-transitory computer readable medium and information processing apparatus and method for classifying multilingual documents
US9262400B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 2, 2014 |
| Grant date | Feb 16, 2016 |
| Priority date | — |
| Expiry date | Oct 2, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/40
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A non-transitory computer readable medium storing a program is provided. A process of the program includes: extracting, concerning first document information including texts, a word sense associated with a word in each text; setting a word sense to be a teacher signal; creating a first topic model by using the teacher signal; estimating a topic of each text by using the first topic model; generating a learning model by using the topic as a feature and the teacher signal as a category; extracting, concerning second document information including texts, a word sense associated with a word in each text; setting a word sense to be a teacher signal; creating a second topic model by using the teacher signal; estimating a topic of each text by using the second topic model; and estimating a category of each text by using the topic as a feature and the learning model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.