Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria
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.