| 研究課題/領域番号 |
21K17816
|
|---|
| 研究機関 | 北陸先端科学技術大学院大学 |
|---|
研究代表者 |
K. Natthawut 北陸先端科学技術大学院大学, 先端科学技術研究科, 助教 (40818100)
|
|---|
| 研究期間 (年度) |
2021-04-01 – 2023-03-31
|
| キーワード | Temporal Knowledge Graph / Knowledge Extraction |
|---|
| 研究実績の概要 |
This research aims to propose a framework to construct a temporal knowledge graph from the text. So far, we have proposed the knowledge extraction framework for extracting useful knowledge from a text by using both semantic and syntactic features. Our framework is up to 20% improvement compared with the state-of-the-art methods. Also, we manually built the temporal knowledge graph as the bootstrapping training data and prepared the dataset for extracting temporal clues in the financial domain. We selected the financial domain for this study because the financial data are extremely sensitive to temporal information.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
The research project is progressed as scheduled. The preliminary framework for extracting knowledge is implemented. Also, we obtained the data and the initial results for further experiments.
|
| 今後の研究の推進方策 |
We plan to utilize the collected data in the financial domain to build the model for the temporal knowledge graph construction framework. Also, we plan to improve the temporal clue extraction from text based on our collected data.
|
| 次年度使用額が生じた理由 |
We could not attend the international conference due to the spread of COVID-19. Considering this situation, we will use the travel expenses to buy computing and storage devices in order to carry out further experiments.
|
