Abstract

Newspaper texts, narratives and other such texts describe events which occur in time and specify the temporal location and order of these events. Text comprehension, even at the most general level, involves the capability to identify the events described in a text and locate these in time. Thus, we propose an initial evaluation exercise based on three limited tasks that will drive forward research in the automatic identification of temporal referring expressions, events and temporal relations within a text. We specify three separate tasks that involve identifying event-time and event-event temporal relations. Participants will receive a modified version of TimeBank (183 documents, approx. 2500 sentences) which has had TimeML annotations removed or modified so as contain only the information to be supplied in the test corpus.

Organizers
James Pustejovsky
Department of Computer Science, Brandeis University

Robert Gaizauskas
Department of Computer Science, University of Sheffield

Mark Hepple
Department of Computer Science, University of Sheffield

Graham Katz
Institute for Cognitive Science, University of Osnabürck

Frank Schilder
Research & Development, Thomson Legal & Regulatory

Marc Verhagen
Department of Computer Science, Brandeis University