Abstract
Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a prompting strategy that formulates a number of different NLU tasks as contextual entailment. This approach improves the zero-shot adaptation of pretrained entailment models. Secondly, we notice that self-training entailment-based models with unlabeled data can significantly improve the adaptation performance on downstream tasks. To achieve more stable improvement, we propose the Simple Pseudo-Label Editing (SimPLE) algorithm for better pseudo-labeling quality in self-training. We also found that both pretrained entailment-based models and the self-trained models are robust against adversarial evaluation data. Experiments on binary and multi-class classification tasks show that SimPLE leads to more robust self-training results, indicating that the self-trained entailment models are more efficient and trustworthy than large language models on language understanding tasks.- Anthology ID:
- 2023.acl-long.772
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13803–13817
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.772
- DOI:
- 10.18653/v1/2023.acl-long.772
- Cite (ACL):
- Jiaxin Ge, Hongyin Luo, Yoon Kim, and James Glass. 2023. Entailment as Robust Self-Learner. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13803–13817, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Entailment as Robust Self-Learner (Ge et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.acl-long.772.pdf