# Transduce: learning transduction grammars for string transformation

arXiv: https://arxiv.org/abs/2401.09426 · HTML: https://mlsanity.com/paper/2401.09426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 0 of its 3 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Abstract (arXiv)

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.