Reasoning about Goals, Steps, and Temporal Ordering with WikiHow

Li Zhang, Qing Lyu, Chris Callison-Burch
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
We propose a suite of reasoning tasks on two types of relations between procedural events: GOAL-STEP relations ("learn poses" is a step in the larger goal of "doing yoga") and STEP-STEP TEMPORAL relations ("buy a yoga mat" typically precedes "learn poses"). We introduce a dataset targeting these two relations based on wikiHow, a website of instructional how-to articles. Our human-validated test set serves as a reliable benchmark for commonsense inference, with a gap of about 10% to 20% between
more » ... he performance of state-ofthe-art transformer models and human performance. Our automatically-generated training set allows models to effectively transfer to outof-domain tasks requiring knowledge of procedural events, with greatly improved performances on SWAG, Snips, and Story Cloze Test in zero-and few-shot settings.
doi:10.18653/v1/2020.emnlp-main.374 fatcat:ifaldoer2bbxnmyy7ahiv6ovaa