Local and Global Feature Extraction for Senses and its application to Topic Tracking
Project/Area Number |
25330255
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | University of Yamanashi |
Principal Investigator |
|
Co-Investigator(Renkei-kenkyūsha) |
SUZUKI TOMOHIRO 山梨大学, 大学院総合研究部, 准教授 (70235977)
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2013: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
|
Keywords | 分野語義辞書 / 転移学習 / 素性選択 / 文書分類 / 続報記事抽出 / 時系列テキストデータ / 意味処理 / 話題語 / 背景語 / 続報記事 / 時系列データ処理 |
Outline of Final Research Achievements |
This study proposed a method for lexical semantic extraction which is effective for topic tracking and text categorization that training data may derive from a difference time period from the test data. We present a method that minimizes the impact of temporal effects by using term smoothing and transfer learning techniques. The results showed that integrating term smoothing and transfer learning improves overall performance of topic tracking and text categorization, especially it is effective when the creation time period of the test data differs greatly from the training data.
|
Report
(4 results)
Research Products
(14 results)