Acquisition of Knowledge Frame with Denotational and Connotational Meanings and its Application to Text Understanding
Project/Area Number |
18H03286
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Review Section |
Basic Section 61030:Intelligent informatics-related
|
Research Institution | Waseda University (2020) Kyoto University (2018-2019) |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
笹野 遼平 名古屋大学, 情報学研究科, 准教授 (70603918)
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥17,290,000 (Direct Cost: ¥13,300,000、Indirect Cost: ¥3,990,000)
Fiscal Year 2020: ¥5,460,000 (Direct Cost: ¥4,200,000、Indirect Cost: ¥1,260,000)
Fiscal Year 2019: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Fiscal Year 2018: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
|
Keywords | 言語理解 / 知識フレーム / 言内の意味 / 言外の意味 / 述語項構造 |
Outline of Final Research Achievements |
We have acquired knowledge about denotation and connotation for case frames and "events" based on predicate-argument structures to achieve natural language understanding. For denotation knowledge, we mapped case frames to semantic frames of FrameNet and induced semantic frames using deep learning techniques. For connotation knowledge, we gradually acquired emotion knowledge for events. We also devised a method to use knowledge in deep learning models.
|
Academic Significance and Societal Importance of the Research Achievements |
従来の自動構築された格フレームは言内・言外ともに意味知識をもっておらず、統語的な言い換えは認識できても、意味的な同義関係は認識できなかった。本研究の成果はこれらの知識を獲得したもので、計算機による自然言語の意味理解に一歩踏み出すことができたと考える。今後の展開として、本研究の成果を利用することによって情報アクセス技術を高度化し、情報の取得や利活用といった人間の基本的な知的活動を強力に支援することができるようになると期待できる。
|
Report
(4 results)
Research Products
(12 results)