Erwin Marsi, Pinar Øzturk, Murat V. Ardelan
We report on a demonstration system for text mining of literature in marine science and related disciplines. It automatically extracts variables (e.g.
CO2) involved in events of change/increase/decrease (e.g increasing CO2), as well as co-occurrence and causal relations among these events (e.g.
increasing CO2 causes a decrease in pH in seawater), resulting in a big knowledge graph. A web-based graphical user interface targeted at marine sci- entists facilitates searching, browsing and visualising events and their relations in an interactive way.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados