Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria
Venue
IJCNLP-ACL(2009)
Publication Year
2009
Authors
Gregory Druck, Gideon S. Mann, Andrew McCallum
BibTeX
Abstract
In this paper, we propose a novel method for semi-supervised learning of
nonprojective log-linear dependency parsers using directly expressed linguistic
prior knowledge (e.g. a noun’s parent is often a verb). Model parameters are
estimated using a generalized expectation (GE) objective function that penalizes
the mismatch between model predictions and linguistic expectation constraints. In a
comparison with two prominent “unsupervised” learning methods that require indirect
biasing toward the correct syntactic structure, we show that GE can attain better
accuracy with as few as 20 intuitive constraints. We also present positive
experimental results on longer sentences in multiple languages.