Paper: Unsupervised Spectral Learning of WCFG as Low-rank Matrix Completion

ACL ID D13-1059
Title Unsupervised Spectral Learning of WCFG as Low-rank Matrix Completion
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

We derive a spectral method for unsupervised learning of Weighted Context Free Grammars. We frame WCFG induction as finding a Han- kel matrix that has low rank and is linearly constrained to represent a function computed by inside-outside recursions. The proposed al- gorithm picks the grammar that agrees with a sample and is the simplest with respect to the nuclear norm of the Hankel matrix.