Abstract
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in entailment models via only a handful of rule templates. Second, to make the entailment model—a discriminator—more robust, we propose the first GAN-style approach for training it using a natural language example generator that iteratively adjusts to the discriminator’s weaknesses. We demonstrate effectiveness using two entailment datasets, where the proposed methods increase accuracy by 4.7% on SciTail and by 2.8% on a 1% sub-sample of SNLI. Notably, even a single hand-written rule, negate, improves the accuracy of negation examples in SNLI by 6.1%.- Anthology ID:
- P18-1225
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2418–2428
- Language:
- URL:
- https://aclanthology.org/P18-1225
- DOI:
- 10.18653/v1/P18-1225
- Cite (ACL):
- Dongyeop Kang, Tushar Khot, Ashish Sabharwal, and Eduard Hovy. 2018. AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2418–2428, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples (Kang et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P18-1225.pdf
- Code
- dykang/adventure
- Data
- SICK, SNLI, SQuAD