2010 Fiscal Year Final Research Report
Retrieving Bilingual Documents based on Word Sense and its Application to Topic Tracking
| Project/Area Number |
20500128
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | University of Yamanashi |
|---|
Principal Investigator |
FUKUMOTO Fumiyo University of Yamanashi, 大学院・医学工学総合研究部, 教授 (60262648)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Keywords | 多義解消 / クラスタリング / 照応解析 / 続報記事抽出 / 多言語コーパス / 教師なし学習 |
|---|
| Research Abstract |
With the exponential growth of information on the Internet, it is becoming increasingly difficult to find and organize relevant materials. Topic tracking is a research to attack the problem. One of the major problems in the tracking task is how to make a clear distinction between a topic and an event. A wide range of statistical and machine learning techniques have been applied to topic tracking. However, one encounters quite a large number of referring expressions and ambiguous word senses. We proposed a topic tracking approach based on semantic analysis, especially we focused on word sense disambiguation, overt pronoun resolutions and retrieving relevant documents by using cross-language category hierarchies.
|
