Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
arXiv:1909.04745
Abstract
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
arXiv commentAccepted to EMNLP 2019 as a long paper. This revision fixed a typo in an author name in references
References in corpus (8)
- ADADELTA: An Adaptive Learning Rate Method
- Bidirectional Attention Flow for Machine Comprehension
- Tracking the World State with Recurrent Entity Networks
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- A Neural Knowledge Language Model
- Query-Reduction Networks for Question Answering
- What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text
- Reasoning about Actions and State Changes by Injecting Commonsense Knowledge