| Project/Area Number |
17K00324
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Kushiro National College of Technology |
|---|
Principal Investigator |
Nakajima Yoko 釧路工業高等専門学校, 創造工学科, 准教授 (20217730)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
プタシンスキ ミハウ 北見工業大学, 工学部, 准教授 (60711504)
桝井 文人 北見工業大学, 工学部, 教授 (80324549)
本間 宏利 釧路工業高等専門学校, 創造工学科, 准教授 (80249721)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 自然言語処理 / 意味役割 / 将来言及文 / 未来動向予測支援 / 形態パターン / 機械学習 / 分類モデル / 情報抽出 / 未来動向予測 / 未来語 / 単語極性情報 / 意味役割付与 |
|---|
| Outline of Final Research Achievements |
In this research, we developed a versatile future trend prediction support system using future reference sentences extracted automatically from news articles.
To achieve that, we firstly developed a method to classify and extract implicit and explicit future reference sentences without the use of simple keywords, and confirmed that it is possible to generate a classification model with a small amount of useful learning data by using a Language Combinatorics-based learning method.Next, we applied automatic future reference extraction to develop a method to support future trend prediction using only future reference sentences, with no need for expert knowledge.The usefulness of the system as a whole was verified in experiments in which sentences referring to the future were extracted from news articles and related to them events were predicted in 1-2 years later.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究成果は，従来手法の手がかり表現のような限定的な語を用いることなく，文中に混在する潜在的意味を持つどのような文に対しても応用可能であり有用な文を取得する手法として貢献できると考える．また，従来手法とは違う手法で未来予測の可能性を示したことは，他分野への発展が期待できる．本システムは，専門的知識を持たずとも近年1，2年の将来言及するデータをもとに企業・政策活動などにおいて，中・長期戦略などで必要となる先を見通すための支援に応用が可能であり，さらには，社会技術イノベーション創出に貢献できると考える．
|
