Abstract
Codifying commonsense knowledge in machines is a longstanding goal of artificial intelligence. Recently, much progress toward this goal has been made with automatic knowledge base (KB) construction techniques. However, such techniques focus primarily on the acquisition of positive (true) KB statements, even though negative (false) statements are often also important for discriminative reasoning over commonsense KBs. As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). Importantly, as most KBs do not contain negatives, NegatER relies only on the positive knowledge in the LM and does not require ground-truth negative examples. Experiments demonstrate that, compared to multiple contrastive data augmentation approaches, NegatER yields negatives that are more grammatical, coherent, and informative—leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be “re-purposed” to generate negative knowledge.- Anthology ID:
- 2021.emnlp-main.456
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5633–5646
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.456
- DOI:
- 10.18653/v1/2021.emnlp-main.456
- Cite (ACL):
- Tara Safavi, Jing Zhu, and Danai Koutra. 2021. NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5633–5646, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases (Safavi et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.456.pdf
- Code
- tsafavi/negater