Semantic Patterns to Structure TimeFrames in Text’
Abstract
Event ordering is a very important task in the event extraction field since any analysis of the causality and impacts of a specific action or a change requires consideration of temporality and ordering. Many pattern-based approaches or machine learning approaches work on identifying the events in the text and creating relationships between them. In this paper, we present a novel approach based on timeframes, that will enable distinction between multiple timeframes in a text, when available, and grouping events within these timeframes.