Project/Area Number |
23500121
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Media informatics/Database
|
Research Institution | Tokyo Institute of Technology (2013-2014) Nara Institute of Science and Technology (2011-2012) |
Principal Investigator |
MIYAZAKI Jun 東京工業大学, 情報理工学(系)研究科, 教授 (40293394)
|
Project Period (FY) |
2011-04-28 – 2015-03-31
|
Project Status |
Completed (Fiscal Year 2014)
|
Budget Amount *help |
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2012: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2011: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
Keywords | 情報検索 / 構造化文書 / XML / 文書統計量 / メニーコアプロセッサ / XML文書 / XML文書検索 / 更新処理 / 問合せ処理 / 高性能計算 / 部分文書検索 / 高精度検索 / マルチコアプロセッサ |
Outline of Final Research Achievements |
In this project, we have studied on an efficient calculation of document statistics taking account of use of manycore processors and a method for fast updates of structured documents, in particular, XML documents such as Wikipedia, in response to their frequent modifications by many users with keeping its effective retrieval as well as fast query processing, so that these dynamically updated documents can always be retrieved precisely and efficiently. In order to improve the efficiency of the updates of documents, we have proposed new term indexing schema and two filters to avoid inserting noisy terms into the indices. In addition, we have also proposed a method to efficiently calculate document statistics by using a manycore GPGPU. The experimental results showed that the cost of document updates can reduce up to 25% due to the new indices and filters without deteriorating its precision, and the GPGPU can lead to more than 10x faster calculation of document statistics than a CPU.
|