Experiments with Reasoning for Temporal Relations between Events

摘要

Few attempts have been made to investigate the utility of temporal reasoning within machine learning frameworks for temporal relation classification between events in news articles. This paper presents three settings where temporal reasoning aids machine learned classifiers of temporal relations: (1) expansion of the dataset used for learning; (2) detection of inconsistencies among the automatically identified relations; and (3) selection among multiple temporal relations. Feature engineering is another effort in our work to improve classification accuracy.