Textual Features for Programming by Example

Aditya Menon, Omer Tamuz, Sumit Gulwani, Adam Kalai, and Butler Lampson


Citation: Textual features for programming by example. CoRR abs/1209.3811 (Sept, 2012) (with Aditya Menon, Omer Tamuz, Sumit Gulwani, and Adam Kalai)

Links: Abstract, Acrobat

Email: blampson@microsoft.com. This paper is at http://www.research.microsoft.com.



In Programming by Example, a system attempts to infer a program from input and output examples, generally by searching for a composition of certain base functions. Performing a naıve brute force search is infeasible for even mildly involved tasks. We note that the examples themselves often present clues as to which functions to compose, and how to rank the resulting programs. In text processing, which is our domain of interest, clues arise from simple textual features: for example, if parts of the input and output strings are permutations of one another, this suggests that sorting may be useful. We describe a system that learns the reliability of such clues, allowing for faster search and a principled ranking over programs. Experiments on a prototype of this system show that this learning scheme facilitates efficient inference on a range of text processing tasks.