Computing Implicit Entities and Events with Getaruns (short paper)

In order to show that a system for text understanding has produced a sound representation of the semantic and pragmatic contents of a story, it should be able to answer questions about the participants and the events occurring in the story. This requires processing linguistic descriptions which are lexically expressed but also unexpressed ones, a task that, in our opinion, can only be accomplished starting from full-fledged semantic representations. The overall task of story understanding requires in addition computing appropriate coreference and cospecification for entities and events in what is usually referred to as a Discourse Model. All these tasks have been implemented in the GETARUNS system, which is subdivided into two main meta-modules or levels: the Low Level System, containing all modules that operate at sentence level; High Level System, containing all the modules that operate at discourse level by updating the Discourse Model. The system is divided up into a pipeline of sequential but independent modules which realize the subdivision of a parsing scheme as proposed in LFG theory where a c-structure is built before the f-structure can be projected by unification into a DAG (Direct Acyclic Graph). In this sense we try to apply phrase-structure rules in a given sequence as they are ordered in the grammar: whenever a syntactic constituent is successfully built, it is checked for semantic consistency, as LFG grammaticality principles require [1]. GETARUNS has a highly sophisticated linguistically based semantic module which is used to build up the Discourse Model. Semantic processing is strongly modularized and distributed amongst a number of different submodules which take care of Spatio-Temporal Reasoning, Discourse Level Anaphora Resolution, and other subsidiary processes like Topic Hierarchy which cooperate to find the most probable antecedent of coreferring