| Project/Area Number |
23300053
|
|---|
| 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 |
OKUMURA MANABU 東京工業大学, 精密工学研究所, 教授 (60214079)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TAKAMURA Hiroya 東京工業大学, 精密工学研究所, 准教授 (80361773)
FUJITA Atsushi 公立はこだて未来大学, システム情報科学科, 准教授 (10402801)
INUI Takashi 筑波大学, システム情報工学研究科(系), 助教 (60397031)
SASANO Ryohei 東京工業大学, 精密工学研究所, 助教 (70603918)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
HIRAO Tsutomu 日本電信電話株式会社, NTTコミュニケーション科学基礎研究所, 研究員 (40396148)
|
|---|
| Project Period (FY) |
2011-04-01 – 2014-03-31
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥19,890,000 (Direct Cost: ¥15,300,000、Indirect Cost: ¥4,590,000)
Fiscal Year 2013: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2012: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2011: ¥10,270,000 (Direct Cost: ¥7,900,000、Indirect Cost: ¥2,370,000)
|
|---|
| Keywords | 評判情報抽出 / 評判要約 / 言い換え / 属性体系構築 / ゼロ照応解析 |
|---|
| Research Abstract |
We proposed a new method of extracting tuples of an object, its attribute, and an evaluative expression from a document, by leveraging the techniques in semantic role labeling. Since structured output learning is considered to be a promising method in semantic role labeling, our method is also based on it. Furthermore, we proposed a new sentiment summarization method that aggregates a set of pairs of an attribute and an evaluative expression, by taking into account their synonym relationships. The proposed method is based on the model
that we proposed for text summarization, based on Facility Location Problem.
|
