Beyond plain spatial knowledge: Determining where entities are and are not located, and for how long

Abstract

This paper complements semantic role representations with spatial knowledge beyond indicating plain locations. Namely, we extract where entities are (and are not) located, and for how long (seconds, hours, days, etc.). Crowdsourced annotations show that this additional knowledge is intuitive to humans and can be annotated by non-experts. Experimental results show that the task can be automated.