Automatic story generation systems require a collection of commonsense knowledge to generate stories that contain logical and coherent sequences of events appropriate for their intended audience. But manually building and populating a semantic ontology that contains relevant assertions is a tedious task. Crowdsourcing can be used as an approach to quickly amass a large collection of commonsense concepts but requires validation of the quality of the knowledge that has been contributed by the public. Another approach is through relation extraction. This paper discusses the use of GATE and custom extraction rules to automatically extract binary conceptual relations from children's stories. Evaluation results show that the extractor achieved a very low overall accuracy of only 36% based on precision, recall and F-measure. The use of incomplete and generalized extraction patterns, insufficient text indicators, accuracy of existing tools, and inability to infer and detect implied relations were the major causes of the low accuracy scores.
