Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data

Yoshinaka, Ryo

doi:10.1007/978-3-642-04414-4_24

Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data

Ryo Yoshinaka

ALT 2009 pp. 278-292

doi:10.1007/978-3-642-04414-4_24 /alt/2009/yoshinaka2009alt-learning/

Abstract

Recently Clark and Eyraud (2007) have shown that substitutable context-free languages, which capture an aspect of natural language phenomena, are efficiently identifiable in the limit from positive data. Generalizing their work, this paper presents a polynomial-time learning algorithm for new subclasses of mildly context-sensitive languages with variants of substitutability.

PDF ALT Semantic Scholar

Cite

Text

Yoshinaka. "Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data." International Conference on Algorithmic Learning Theory, 2009. doi:10.1007/978-3-642-04414-4_24

Markdown

[Yoshinaka. "Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data." International Conference on Algorithmic Learning Theory, 2009.](https://mlanthology.org/alt/2009/yoshinaka2009alt-learning/) doi:10.1007/978-3-642-04414-4_24

BibTeX

@inproceedings{yoshinaka2009alt-learning,
  title     = {{Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data}},
  author    = {Yoshinaka, Ryo},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2009},
  pages     = {278-292},
  doi       = {10.1007/978-3-642-04414-4_24},
  url       = {https://mlanthology.org/alt/2009/yoshinaka2009alt-learning/}
}