Paper: Semi-Supervised Convex Training for Dependency Parsing

ACL ID P08-1061
Title Semi-Supervised Convex Training for Dependency Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008

We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a dis- criminative, convex, semi-supervised learning algorithm can be obtained that is applicable to large-scale problems. To demonstrate the benefits of this approach, we apply the tech- nique to learning dependency parsers from combined labeled and unlabeled corpora. Us- ing a stochastic gradient descent algorithm, a parsing model can be efficiently learned from semi-supervised data that significantly outper- forms corresponding supervised methods.