Named entity recognition using Linked Open Data and its application to information retrieval
| Project/Area Number |
25280035
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Multimedia database
|
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KANDO Noriko 国立情報学研究所, 情報社会相関研究系, 教授 (80270445)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥11,050,000 (Direct Cost: ¥8,500,000、Indirect Cost: ¥2,550,000)
Fiscal Year 2015: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2014: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2013: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
|
|---|
| Keywords | 情報検索 / 固有名抽出 / Linked Open Data / 多観点分析 |
|---|
| Outline of Final Research Achievements |
In this research, we proposed a framework to extract named entity from the text with named entity type information by using DBPedia. We also proposed facet-biased topic model that take into account the type of named entity as facet. In addition, we implemented WC3 that analyzes consistency of metadata in articles that belongs to a particular Wikipedia category. We confirmed that WC3 can find out the articles that have inconsistent metadata and candidate articles for the category.
|
Report
(4 results)
Research Products
(16 results)
