Bootstrapping statistical parsers from small datasets

We present a practical co-training method for bootstrapping statistical parsers using a small amount of manually parsed training material and a much larger pool of raw sentences. Experimental results show that unlabelled sentences can be used to improve the performance of statistical parsers. In addition, we consider the problem of bootstrapping parsers when the manually parsed training material is in a different domain to either the raw sentences or the testing material. We show that bootstrapping continues to be useful, even though no manually produced parses from the target domain are used.

• Type: Conference
• Year: 2003
• Where: EACL
• Authors: Mark Steedman, Anoop Sarkar, Miles Osborne, Rebecca Hwa, Stephen Clark, Julia Hockenmaier, Paul Ruhlen, Steven Baker, Jeremiah Crim
• Keywords: EACL 2003, Natural Language Processing, Parsed Training Material, Raw Sentences, Statistical Parsers