2018 Fiscal Year Final Research Report
Framework for context-sensitive fact extraction over web data.
Project/Area Number |
17K12786
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Web informatics, Service informatics
|
Research Institution | National Institute of Advanced Industrial Science and Technology |
Principal Investigator |
LEBLAY Julien 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員 (70757377)
|
Project Period (FY) |
2017-04-01 – 2019-03-31
|
Keywords | 文脈依存推論 / 機械学習 / 時間知識グラフ |
Outline of Final Research Achievements |
In this project, we developed tools and techniques to extract context (mostly temporal) from knowledge graphs, one of the prominent model for representing and publishing data on the web, and survey real world applications. This led to an extensive survey and tutorial focusing on applications to data journalism. We implementing a prototype application based on some earlier work defining a language to reasoning about the context of ontological data in the presence of uncertainty and incompleteness. In parallel, we investigated machine learning approaches to automatically infer the validity over time of the facts in a knowledge graph.
|
Free Research Field |
情報科学
|
Academic Significance and Societal Importance of the Research Achievements |
We published one survey paper and one demonstration poster and two tutorials in international conferences, and one paper in an international workshop. We are extending this work with neural network-based models, and plan to explore non-temporal contexts in the future.
|