USFD: preliminary exploration of features and classifiers for the TempEval-2007 tasks

We describe the Sheffield system used in TempEval-2007. Our system takes a machine-learning (ML) based approach, treating temporal relation assignment as a simple classification task and using features easily derived from the TempEval data, i.e. which do not require 'deeper' NLP analysis. We aimed to explore three questions: (1) How well would a 'lite' approach of this kind perform? (2) Which features contribute positively to system performance? (3) Which ML algorithm is better suited for the TempEval tasks? We used the Weka ML workbench to facilitate experimenting with different ML algorithms. The paper describes our system and supplies preliminary answers to the above questions.