Transduce: learning transduction grammars for string transformation
Machine Learning
2024-01-19 v1
Abstract
The synthesis of string transformation programs from input-output examples utilizes various techniques, all based on an inductive bias that comprises a restricted set of basic operators to be combined. A new algorithm, Transduce, is proposed, which is founded on the construction of abstract transduction grammars and their generalization. We experimentally demonstrate that Transduce can learn positional transformations efficiently from one or two positive examples without inductive bias, achieving a success rate higher than the current state of the art.
Keywords
Cite
@article{arxiv.2401.09426,
title = {Transduce: learning transduction grammars for string transformation},
author = {Francis Frydman and Philippe Mangion},
journal= {arXiv preprint arXiv:2401.09426},
year = {2024}
}