Abstract
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 common-sense inference, with a gap of about 10% to 20% between the performance of state-of-the-art transformer models and human performance. Our automatically-generated training set allows models to effectively transfer to out-of-domain tasks requiring knowledge of procedural events, with greatly improved performances on SWAG, Snips, and Story Cloze Test in zero- and few-shot settings.- Anthology ID:
- 2020.emnlp-main.374
- Original:
- 2020.emnlp-main.374v1
- Version 2:
- 2020.emnlp-main.374v2
- Version 3:
- 2020.emnlp-main.374v3
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4630–4639
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.374
- DOI:
- 10.18653/v1/2020.emnlp-main.374
- Cite (ACL):
- Li Zhang, Qing Lyu, and Chris Callison-Burch. 2020. Reasoning about Goals, Steps, and Temporal Ordering with WikiHow. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4630–4639, Online. Association for Computational Linguistics.
- Cite (Informal):
- Reasoning about Goals, Steps, and Temporal Ordering with WikiHow (Zhang et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.374.pdf
- Code
- zharry29/wikihow-goal-step
- Data
- ROCStories, SNIPS, SWAG, WikiHow