Acquisition of cross-word frame knowledge from large texts and its application to semantic analysis
Project/Area Number |
16K16110
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Intelligent informatics
|
Research Institution | Nagoya University (2017-2019) Tokyo Institute of Technology (2016) |
Principal Investigator |
SASANO RYOHEI 名古屋大学, 情報学研究科, 准教授 (70603918)
|
Project Period (FY) |
2016-04-01 – 2020-03-31
|
Project Status |
Completed (Fiscal Year 2019)
|
Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
Keywords | 格フレーム / 意味役割付与 / 単語ベクトル / FrameNet / 意味ベクトル / 意味役割 / 格と語順 / 自然言語処理 |
Outline of Final Research Achievements |
In this research project, we constructed cross-word frame knowledge by linking the Kyoto University case frames, which is automatically acquired frame knowledge, to the manually-crafted frame knowledge FrameNet and developed a Japanese semantic role labeling system based on the constructed frame knowledge. In addition, we investigated the distribution of words that belong to a certain word class in a pre-trained word vector space to improve the accuracy of frame mapping between different lexicons and different languages.
|
Academic Significance and Societal Importance of the Research Achievements |
本研究では,自動獲得されたフレーム知識を,人手で整備されたフレーム知識に対応付けることで,語横断的な,言語横断的なフレーム知識を構築できることを示した.さらに,構築した知識を用いることで,英語を対象に構築された意味役割タグ付きコーパスから,日本語意味役割付与システムを構築できることを示した.また,特定の意味クラスに属する単語ベクトルが意味ベクトル空間においてどのように分布しているかに関する分析は,単語ベクトルを用いたシステムの構築において有用な知見となると期待できる.
|
Report
(5 results)
Research Products
(9 results)