Paper: Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria

ACL ID P09-1041
Title Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

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 us- ing a generalized expectation (GE) objec- tive function that penalizes the mismatch between model predictions and linguistic expectation constraints. In a comparison with two prominent “unsupervised” learn- ing 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.