Abstract
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.- Anthology ID:
- 2021.inlg-1.19
- Original:
- 2021.inlg-1.19v1
- Version 2:
- 2021.inlg-1.19v2
- Volume:
- Proceedings of the 14th International Conference on Natural Language Generation
- Month:
- August
- Year:
- 2021
- Address:
- Aberdeen, Scotland, UK
- Editors:
- Anya Belz, Angela Fan, Ehud Reiter, Yaji Sripada
- Venue:
- INLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 184–200
- Language:
- URL:
- https://aclanthology.org/2021.inlg-1.19
- DOI:
- 10.18653/v1/2021.inlg-1.19
- Cite (ACL):
- Qing Lyu, Li Zhang, and Chris Callison-Burch. 2021. Goal-Oriented Script Construction. In Proceedings of the 14th International Conference on Natural Language Generation, pages 184–200, Aberdeen, Scotland, UK. Association for Computational Linguistics.
- Cite (Informal):
- Goal-Oriented Script Construction (Lyu et al., INLG 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.inlg-1.19.pdf
- Code
- veronica320/wikihow-gosc
- Data
- WikiHow