Textual Features for Programming by Example

TL;DR

This paper introduces a system that leverages textual features to improve program inference in Programming by Example, enabling faster search and better ranking of candidate programs for text processing tasks.

Contribution

It presents a novel learning approach that assesses the reliability of textual clues, enhancing the efficiency and accuracy of program synthesis in text processing.

Findings

Improved inference speed on text processing tasks

Effective ranking of candidate programs based on learned clues

Demonstrated success on a prototype system

Abstract

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 naive 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.