Abstract
Neural models and symbolic rules such as regular expressions have their respective merits and weaknesses. In this paper, we study the integration of the two approaches for the slot filling task by converting regular expressions into neural networks. Specifically, we first convert regular expressions into a special form of finite-state transducers, then unfold its approximate inference algorithm as a bidirectional recurrent neural model that performs slot filling via sequence labeling. Experimental results show that our model has superior zero-shot and few-shot performance and stays competitive when there are sufficient training data.- Anthology ID:
- 2021.emnlp-main.747
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9481–9498
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.747
- DOI:
- 10.18653/v1/2021.emnlp-main.747
- Cite (ACL):
- Chengyue Jiang, Zijian Jin, and Kewei Tu. 2021. Neuralizing Regular Expressions for Slot Filling. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9481–9498, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Neuralizing Regular Expressions for Slot Filling (Jiang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.emnlp-main.747.pdf
- Data
- ATIS