Abstract
Unfamiliar terminology and complex language can present barriers to understanding science. Natural language processing stands to help address these issues by automatically defining unfamiliar terms. We introduce a new task and dataset for defining scientific terms and controlling the complexity of generated definitions as a way of adapting to a specific reader’s background knowledge. We test four definition generation methods for this new task, finding that a sequence-to-sequence approach is most successful. We then explore the version of the task in which definitions are generated at a target complexity level. We introduce a novel reranking approach and find in human evaluations that it offers superior fluency while also controlling complexity, compared to several controllable generation baselines.- Anthology ID:
- 2022.acl-long.569
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8298–8317
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.569
- DOI:
- 10.18653/v1/2022.acl-long.569
- Cite (ACL):
- Tal August, Katharina Reinecke, and Noah A. Smith. 2022. Generating Scientific Definitions with Controllable Complexity. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8298–8317, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Generating Scientific Definitions with Controllable Complexity (August et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.acl-long.569.pdf
- Code
- talaugust/definition-complexity