Optimizing Spectral Learning for Parsing

06/07/2016
by   Shashi Narayan, et al.
0

We describe a search algorithm for optimizing the number of latent states when estimating latent-variable PCFGs with spectral methods. Our results show that contrary to the common belief that the number of latent states for each nonterminal in an L-PCFG can be decided in isolation with spectral methods, parsing results significantly improve if the number of latent states for each nonterminal is globally optimized, while taking into account interactions between the different nonterminals. In addition, we contribute an empirical analysis of spectral algorithms on eight morphologically rich languages: Basque, French, German, Hebrew, Hungarian, Korean, Polish and Swedish. Our results show that our estimation consistently performs better or close to coarse-to-fine expectation-maximization techniques for these languages.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/16/2012

A Spectral Algorithm for Latent Junction Trees

Latent variable models are an elegant framework for capturing rich proba...
research
07/12/2014

A Spectral Algorithm for Inference in Hidden Semi-Markov Models

Hidden semi-Markov models (HSMMs) are latent variable models which allow...
research
06/11/2018

Growing Better Graphs With Latent-Variable Probabilistic Graph Grammars

Recent work in graph models has found that probabilistic hyperedge repla...
research
05/28/2020

Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models

Although with progress in introducing auxiliary amortized inference mode...
research
05/18/2009

A statistical learning approach to color demosaicing

A statistical learning/inference framework for color demosaicing is pres...
research
06/07/2020

Tensors over Semirings for Latent-Variable Weighted Logic Programs

Semiring parsing is an elegant framework for describing parsers by using...
research
06/27/2012

Local Loss Optimization in Operator Models: A New Insight into Spectral Learning

This paper re-visits the spectral method for learning latent variable mo...

Please sign up or login with your details

Forgot password? Click here to reset