LIMSI at SemEval-2016 Task 12: machine-learning and temporal information to identify clinical events and time expressions

Our experiments rely on a combination of machine-learning (CRF) and rule-based (HeidelTime) systems. First, a CRF system identifies both EVENTS and TIMEX3, along with polarity values for EVENT and types of TIMEX. Second, the HeidelTime tool identifies DOCTIME and TIMEX3 elements, and computes DocTimeRel for each EVENT identified by the CRF. Third, another CRF system computes DocTimeRel for each previously identified EVENT, based on DocTimeRel computed by HeidelTime. In the first submission, all EVENTS and TIMEX3 are identified through one general CRF model while in the second submission, we combined two CRF models (one for both EVENT and TIMEX3, and one only for TIMEX3) and we applied post-processing rules on the outputs.