| Project/Area Number |
17H01828
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Library and information science/Humanistic social informatics
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
Jatowt Adam 京都大学, 情報学研究科, 特定准教授 (00415861)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
澄川 靖信 東京都立大学, 大学教育センター, 助教 (70756303)
Zhang Yating 国立研究開発法人理化学研究所, 革新知能統合研究センター, 特別研究員 (30793559)
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥15,080,000 (Direct Cost: ¥11,600,000、Indirect Cost: ¥3,480,000)
Fiscal Year 2020: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2018: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2017: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
|
|---|
| Keywords | news archives / digital history / collective memory / digital archives / computational history / temporal information / question answering / document archives / digital libraries / summarization / entity similarity / news archive mining / temporal analogy / text mining / information service |
|---|
| Outline of Final Research Achievements |
The project has resulted in the development of many novel approaches to analyze and understand history both based on primary sources (e.g., news articles) or secondary sources (e.g., Wikipedia). We have proposed new research tasks such as detection of analogy over time, clustering entities based on their shared or similar histories, answering questions related to the past, search models for archival documents and automatically building timelines. In the process of this research several datasets have been also developed. Given the proposed methods and tools, users who are either processionals or average users can find or understand content related to history in easier and more effective way. Our society digitizes massive data from the past such as old books and news articles, however so far we had few dedicated computational modes for processing such data. With the outcomes of this project we have generated many novel directions for future research for the academic community.
|
| Academic Significance and Societal Importance of the Research Achievements |
The project resulted in several publications in high impact conferences and journals related to artificial intelligence, data mining and natural language processing such as WSDM, CIKM, ECIR, ECAI, JCDL, IP&M. The proposed models can be e.g. implemented in museums or libraries to attract visitors.
|
