TY - GEN
T1 - On the utility of curricula in unsupervised learning of probabilistic grammars
AU - Tu, Kewei
AU - Honavar, Vasant
PY - 2011
Y1 - 2011
N2 - 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 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.
AB - 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 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.
UR - https://www.scopus.com/pages/publications/84868299604
UR - https://www.scopus.com/pages/publications/84868299604#tab=citedBy
U2 - 10.5591/978-1-57735-516-8/IJCAI11-256
DO - 10.5591/978-1-57735-516-8/IJCAI11-256
M3 - Conference contribution
AN - SCOPUS:84868299604
SN - 9781577355120
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 1523
EP - 1528
BT - IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence
T2 - 22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
Y2 - 16 July 2011 through 22 July 2011
ER -