一切都是有原因的：在程序文本中发现行动的目的
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
摘要：
我们的目标是更好地理解程序文本，例如，一段关于光合作用的文章，不仅预测发生了什么，而且预测为什么有些行动需要在其他行动之前发生。我们的方法建立在先前的过程理解框架上，用于预测行动的影响，也可以识别这些影响所能实现的后续步骤。我们提出了我们的新模型（XPAD），偏向于那些（1）解释更多的段落中的动作和（2）更合理的背景知识的影响预测。我们还扩展了现有的基准数据集程序文本理解，ProPara，通过增加新的任务，解释行动预测其依赖关系。我们发现，XPAD显着优于以前的系统在这项任务上，同时保持在ProPara的原始任务的性能。该数据集可在http://data.allenai.org/propara上获得
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
