Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.09426 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909076188823552 |
|---|---|
| author | Frydman, Francis Mangion, Philippe |
| author_facet | Frydman, Francis Mangion, Philippe |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09426 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Transduce: learning transduction grammars for string transformation Frydman, Francis Mangion, Philippe Machine Learning 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. |
| title | Transduce: learning transduction grammars for string transformation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2401.09426 |