| 研究開始時の研究の概要 |
Knowledge Graph plays a key role in various artificial intelligence applications. Generally, a knowledge graph is built to express static knowledge. Nevertheless, knowledge usually changes over time. A knowledge graph without considering the time does not satisfy the change. Therefore, this project aims to study a temporal knowledge graph and to develop a novel framework for constructing temporal knowledge graphs from text. The outcomes of this research will expand the study on the knowledge graph area and facilitate the time-aware knowledge graph-based applications.
|
| 研究実績の概要 |
This research aims to construct a temporal knowledge graph from textual data. In this fiscal year, we developed FinKG-JP, a temporal Japanese knowledge graph in the financial domain, using annual reports provided by the Financial Services Agency via EDINET. Temporal information, including details from the reports and stock prices, was extracted using our financial ontology as a template. This temporal information is encoded at the edges of the knowledge graph. For the ontology in FinKG-JP, we derived concepts from FinKG and added concepts specific to the Japanese market. Overall, FinKG-JP contains more than 5 million entities.
|
