Date of this Version
Journal of Machine Learning Research
We introduce a spectral learning algorithm for latent-variable PCFGs (Matsuzaki et al., 2005; Petrov et al., 2006). Under a separability (singular value) condition, we prove that the method provides statistically consistent parameter estimates. Our result rests on three theorems: the first gives a tensor form of the inside- outside algorithm for PCFGs; the second shows that the required tensors can be estimated directly from training examples where hidden-variable values are missing; the third gives a PAC-style convergence bound for the estimation method.
latent-variable PCFGs, spectral learning algorithms
Cohen, S. B., Stratos, K., Collins, M., Foster, D. P., & Ungar, L. H. (2014). Spectral Learning of Latent-Variable PCFGs: Algorithms and Sample Complexity. Journal of Machine Learning Research, 15 2399-2449. Retrieved from https://repository.upenn.edu/statistics_papers/137
Date Posted: 27 November 2017
This document has been peer reviewed.