Scientific Discovery as Link Prediction in Influence and Citation Graphs
| Autor: | Fan Luo, Mihai Surdeanu, Gus Hahn-Powell, Marco Antonio Valenzuela-Escárcega |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computer science
05 social sciences Scientific discovery 02 engineering and technology computer.software_genre Graph 0202 electrical engineering electronic engineering information engineering Citation graph 020201 artificial intelligence & image processing Data mining 0509 other social sciences 050904 information & library sciences Citation F1 score computer |
| Zdroj: | TextGraphs@NAACL-HLT |
| Popis: | We introduce a machine learning approach for the identification of “white spaces” in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as “CTCF activates FOXA1”, which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the “near future” with a F1 score of 27 points, and a mean average precision of 68%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|