EVENTI is one of the new tasks of the Evalita 2014 Evaluation campaign for NLP and Speech Tools for Italian.
The purpose of EVENTI (EValuation of Events aNd Temporal Information) is to promote research in Temporal Processing for Italian. This evaluation exercise will provide the chance to test a newly developed language resource, the Ita-TimeBank (Caselli et al., 2011) while making it available to the NLP community as one of the largest manually annotated data sets for Temporal Processing.
In addition a pilot task on Temporal Processing of Historical Texts is organized to foster the collaboration between the NLP and the Digital Humanities communities.
Reference to time is a pervasive phenomenon of human communication, and it is reflected in natural language. Recently, a renewed interest in Temporal Processing has spread in the NLP community. The development of the TimeML Annotation Scheme (Pustejovsky et al., 2003), the release of annotated data and the organization of three open evaluation challenges (TempEval-1, TempEval-2 and TempEval-3) have facilitated the development of temporally aware NLP tools.
Currently, to the best of our knowledge, no complete systems exist for Temporal Processing in Italian, though independent modules for event and temporal expressions processing are available (HeidelTime; Robaldo et al., 2011; Caselli et al., 2011b; Angeli and Uzkoreit, 2013).
In this context, EVENTI wants to promote the development of NLP tools for the extraction of events, temporal expressions and temporal relations from Italian texts.
This task was endorsed by the NewsReader 7th FP Project (ICT-316404).