Tone Understanding of Article based on Word Connotation and Application to Text Summarization
Project/Area Number |
26330247
|
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 |
SUZUKI Yoshimi 山梨大学, 大学院総合研究部, 教授 (20206551)
|
Project Period (FY) |
2014-04-01 – 2018-03-31
|
Project Status |
Completed (Fiscal Year 2017)
|
Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2014: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
Keywords | 主張抽出 / 論調把握 / 論調分類 / 自動要約 / 著者の主張 / 論調分類に関する研究発表 / 論調分類結果を利用した要約 / 文書要約に関する研究発表 |
Outline of Final Research Achievements |
For summarization of the newspaper editorials, it is important to grasp the author 's tone and to find issues and assertions. Therefore, we organized the tone types, and classified them into 4 types (speculation, assertion, hope, suggestion) and extracted issues and arguments. For opinion type classification, we used 4 features: words in sentences, positions of each sentence in the editorial, predicate in sentences, adverb appearing in sentences. We proposed a summarization method for summarization of the editorials, by classifying each sentence into 4 opinion types: speculation, assertion, hope, suggestion.
|
Report
(5 results)
Research Products
(10 results)