%0 Conference Proceedings %T Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text %A Dalvi, Bhavana %A Tandon, Niket %A Bosselut, Antoine %A Yih, Wen-tau %A Clark, Peter %Y Inui, Kentaro %Y Jiang, Jing %Y Ng, Vincent %Y Wan, Xiaojun %S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F dalvi-etal-2019-everything %X Our goal is to better comprehend procedural text, e.g., a paragraph about photosynthesis, by not only predicting what happens, but *why* some actions need to happen before others. Our approach builds on a prior process comprehension framework for predicting actions’ effects, to also identify subsequent steps that those effects enable. We present our new model (XPAD) that biases effect predictions towards those that (1) explain more of the actions in the paragraph and (2) are more plausible with respect to background knowledge. We also extend an existing benchmark dataset for procedural text comprehension, ProPara, by adding the new task of explaining actions by predicting their dependencies. We find that XPAD significantly outperforms prior systems on this task, while maintaining the performance on the original task in ProPara. The dataset is available at http://data.allenai.org/propara %R 10.18653/v1/D19-1457 %U https://aclanthology.org/D19-1457 %U https://doi.org/10.18653/v1/D19-1457 %P 4496-4505