Programming by Example Using Least General Generalizations

Raza, Mohammad; Gulwani, Sumit; Milic-Frayling, Natasa

Abstract

Recent advances in Programming by Example (PBE) have supported new applications to text editing, but existing approaches are limited to simple text strings. In this paper we address transformations in richly formatted documents, using an approach based on the idea of least general generalizations from inductive inference, which avoids the scalability issues faced by state-of-the-art PBE methods. We describe a novel domain specific language (DSL) that expresses transformations over XML structures describing richly formatted content, and a synthesis algorithm that generates a minimal program with respect to a natural subsumption ordering in our DSL. We present experimental results on tasks collected from online help forums, showing an average of 4.17 examples required for task completion.

Citation

Raza, M., Gulwani, S., & Milic-Frayling, N. (2014). Programming by Example Using Least General Generalizations. In AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Articial Intelligence. , (283-290)

• Presentation Conference Type: Edited Proceedings
• Conference Name: Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14)
• Start Date: Jul 27, 2014
• End Date: Jul 31, 2014
• Online Publication Date: Jul 27, 2014
• Publication Date: Jul 27, 2014
• Deposit Date: Sep 15, 2017
• Publisher: Association for Computing Machinery (ACM)
• Volume: 2014-July
• Pages: 283-290
• Book Title: AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Articial Intelligence
• ISBN: 9781577356615
• Public URL: https://nottingham-repository.worktribe.com/output/1108049
• Publisher URL: https://dl.acm.org/doi/abs/10.5555/2893873.2893919
• Related Public URLs: https://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/view/8520