ML Anthology

On the Utility of Curricula in Unsupervised Learning of Probabilistic Grammars

Kewei Tu, Vasant G. Honavar
IJCAI 2011 pp. 1523-1528
doi:10.5591/978-1-57735-516-8/IJCAI11-256 /ijcai/2011/tu2011ijcai-utility/

Abstract

We examine the utility of a curriculum (a means of presenting training samples in a meaningful order) in unsupervised learning of probabilistic grammars. We introduce the {\em incremental construction hypothesis} that explains the benefits of a curriculum in learning grammars and offers some useful insights into the design of curricula as well as learning algorithms. We present results of experiments with (a) carefully crafted synthetic data that provide support for our hypothesis and (b) natural language corpus that demonstrate the utility of curricula in unsupervised learning of probabilistic grammars.

PDF IJCAI Semantic Scholar

Cite

Text

Tu and Honavar. "On the Utility of Curricula in Unsupervised Learning of Probabilistic Grammars." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-256

Markdown

[Tu and Honavar. "On the Utility of Curricula in Unsupervised Learning of Probabilistic Grammars." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/tu2011ijcai-utility/) doi:10.5591/978-1-57735-516-8/IJCAI11-256

BibTeX

@inproceedings{tu2011ijcai-utility,
  title     = {{On the Utility of Curricula in Unsupervised Learning of Probabilistic Grammars}},
  author    = {Tu, Kewei and Honavar, Vasant G.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2011},
  pages     = {1523-1528},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-256},
  url       = {https://mlanthology.org/ijcai/2011/tu2011ijcai-utility/}
}