Classifying Temporal Relations with Rich Linguistic Knowledge

We examine the task of temporal relation classification. Unlike existing approaches to this task, we (1) classify an event-event or eventtime pair as one of the 14 temporal relations defined in the TimeBank corpus, rather than as one of the six relations collapsed from the original 14; (2) employ sophisticated linguistic knowledge derived from a variety of semantic and discourse relations, rather than focusing on morpho-syntactic knowledge; and (3) leverage a novel combination of rule-based and learning-based approaches, rather than relying solely on one or the other. Experiments with the TimeBank corpus demonstrate that our knowledge-rich, hybrid approach yields a 15–16% relative reduction in error over a state-of-the-art learning-based baseline system.