Automatic Rule Induction for Efficient Semi-Supervised Learning

Reid Pryzant, Ziyi Yang, Yichong Xu, Chenguang Zhu, Michael Zeng


Abstract
Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as black-box correlation engines that are difficult to explain and sometimes behave unreliably. In this paper, we propose tackling both of these challenges via Automatic Rule Induction (ARI), a simple and general-purpose framework for the automatic discovery and integration of symbolic rules into pretrained transformer models. First, we extract weak symbolic rules from low-capacity machine learning models trained on small amounts of labeled data. Next, we use an attention mechanism to integrate these rules into high-capacity pretrained transformer models. Last, the rule-augmented system becomes part of a self-training framework to boost supervision signal on unlabeled data. These steps can be layered beneath a variety of existing weak supervision and semi-supervised NLP algorithms in order to improve performance and interpretability. Experiments across nine sequence classification and relation extraction tasks suggest that ARI can improve state-of-the-art methods with no manual effort and minimal computational overhead.
Anthology ID:
2022.findings-emnlp.3
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
28–44
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.3
DOI:
10.18653/v1/2022.findings-emnlp.3
Bibkey:
Cite (ACL):
Reid Pryzant, Ziyi Yang, Yichong Xu, Chenguang Zhu, and Michael Zeng. 2022. Automatic Rule Induction for Efficient Semi-Supervised Learning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 28–44, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Automatic Rule Induction for Efficient Semi-Supervised Learning (Pryzant et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.3.pdf