From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction
Citation
Vacareanu, R., Valenzuela-Escárcega, M. A., Barbosa, G. C., Sharp, R., & Surdeanu, M. (2022). From examples to rules: Neural guided rule synthesis for information extraction. arXiv preprint arXiv:2202.00475.Rights
© 2022. The Author(s). This work uses a Creative Commons CC BY license: https://creativecommons.org/licenses/by/4.0/.Collection Information
This item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.Abstract
While deep learning approaches to information extraction have had many successes, they can be difficult to augment or maintain as needs shift. Rule-based methods, on the other hand, can be more easily modified. However, crafting rules requires expertise in linguistics and the domain of interest, making it infeasible for most users. Here we attempt to combine the advantages of these two directions while mitigating their drawbacks. We adapt recent advances from the adjacent field of program synthesis to information extraction, synthesizing rules from provided examples. We use a transformer-based architecture to guide an enumerative search, and show that this reduces the number of steps that need to be explored before a rule is found. Further, we show that without training the synthesis algorithm on the specific domain, our synthesized rules achieve state-of-the-art performance on the 1-shot scenario of a task that focuses on few-shot learning for relation classification, and competitive performance in the 5-shot scenario. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.Note
Open access journalISBN
9791095546726Version
Final published versionae974a485f413a2113503eed53cd6c53
10.48550/arXiv.2202.00475
Scopus Count
Collections
Except where otherwise noted, this item's license is described as © 2022. The Author(s). This work uses a Creative Commons CC BY license: https://creativecommons.org/licenses/by/4.0/.