Modeling Wikipedia to Automatically Generating Coherent and Associative Expository Articles
| Project/Area Number |
15H02747
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
Fujii Atsushi 東京工業大学, 情報理工学院, 准教授 (30302433)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
徳永 健伸 東京工業大学, 情報理工学院, 教授 (20197875)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥16,250,000 (Direct Cost: ¥12,500,000、Indirect Cost: ¥3,750,000)
Fiscal Year 2017: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥5,850,000 (Direct Cost: ¥4,500,000、Indirect Cost: ¥1,350,000)
Fiscal Year 2015: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
|
|---|
| Keywords | 自然言語処理 / 情報検索 / 人工知能 / 百科事典 / ウィキペディア / 情報の組織化 / 連想 / 用語説明 |
|---|
| Outline of Final Research Achievements |
The purpose of this research is intended to automatically generate expository text for an input term, for which two types of contrastive models are explored. First, because the viewpoints used for explanation can be determined depending on the type of the term in question. Second, the target term is compared with existing terms to generate intuitively understandable explanation. The nature of natural language understanding is explored through the strategic use of these models.
|
Report
(4 results)
Research Products
(13 results)
