Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
复制标题
一切发生都有原因：发现程序文本中动作的目的
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Peter Clark
中科院分区：
文献类型：
--
作者：
Bhavana Dalvi;Niket Tandon;Antoine Bosselut;Wen;Peter Clark
我们的目标是更好地理解程序文本，例如关于光合作用的段落，不仅要预测会发生什么，还要预测“为什么”某些动作需要在其他动作之前发生。我们的方法建立在用于预测操作效果的先前过程理解框架的基础上，还可以识别这些效果所实现的后续步骤。我们提出了我们的新模型（XPAD），该模型将效果预测偏向于（1）解释段落中的更多动作以及（2）在背景知识方面更可信的模型。我们还扩展了用于程序文本理解的现有基准数据集 ProPara，添加了通过预测动作依赖性来解释动作的新任务。我们发现 XPAD 在此任务上的性能显着优于现有系统，同时保持了 ProPara 中原始任务的性能。该数据集可在 http://data.allenai.org/propara 获取
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