Inference of Inversion Transduction Grammars

Abstract

We present the first polynomial algorithm for learning a class of inversion transduction grammars (ITGs) that implement context free transducers -- functions from strings to strings. The class of transductions that we can learn properly includes all subsequential transductions. These algorithms are based on a generalisation of distributional learning; we prove correctness of our algorithm under an identification in the limit model.

Cite

Text

Clark. "Inference of Inversion Transduction Grammars." International Conference on Machine Learning, 2011.

Markdown

[Clark. "Inference of Inversion Transduction Grammars." International Conference on Machine Learning, 2011.](https://mlanthology.org/icml/2011/clark2011icml-inference/)

BibTeX

@inproceedings{clark2011icml-inference,
  title     = {{Inference of Inversion Transduction Grammars}},
  author    = {Clark, Alexander},
  booktitle = {International Conference on Machine Learning},
  year      = {2011},
  pages     = {201-208},
  url       = {https://mlanthology.org/icml/2011/clark2011icml-inference/}
}