Projection-based Acquisition of a Temporal Labeller

Abstract

We present a cross-lingual projection framework for temporal annotations. Automatically obtained TimeML annotations in the English portion of a parallel corpus are transferred to the German translation along a word alignment. Direct projection augmented with shallow heuristic knowledge outperforms the uninformed baseline by 6.64 % F1-measure for events, and by 17.93 % for time expressions. Subsequent training of statistical classifiers on the (imperfect) projected annotations significantly boosts precision by up to 31 % to 83.95 % and 89.52%, respectively. 1