Generating Linear Orders Of Text-Based Events

Events described in textual narratives do not always occur in neat, chronological order but occur, for example, during or overlapping each other or as simultaneous events. Summarizations of narratives, however, benefit from a simpler, linear ordering of events. This paper describes an approach for modeling events in text as event intervals and for generating linear orders of event intervals, useful for the summarization of events or as the basis for question answering systems. Linear orders are derived through reducing the set of thirteen possible event interval relations to a set of only before or equal relations. The mapping of event interval relations into before/after sequences requires the support of additional constraints in order to preserve the original semantics of the events presented in the text and to derive plausible orders of events.