Skip to main content
Unpublished Paper
Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria
  • Gregory Druck
  • Gideon Mann
  • Andrew McCallum, University of Massachusetts - Amherst
In this paper, we propose a novel method for semi-supervised learning of non-projective 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.
Publication Date
This is the pre-published version harvested from CIIR.
Citation Information
Gregory Druck, Gideon Mann and Andrew McCallum. "Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria" (2009)
Available at: