Probabilistic Models for High-Order Projective Dependency Parsing

2015/02/14 by Ma, Xuezhe, Zhao, Hai
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1502.04174

Abstract

This paper presents generalized probabilistic models for high-order projective dependency parsing and an algorithmic framework for learning these statistical models involving dependency trees. Partition functions and marginals for high-order dependency trees can be computed efficiently, by adapting our algorithms which extend the inside-outside algorithm to higher-order cases. To show the effectiveness of our algorithms, we perform experiments on three languages---English, Chinese and Czech, using maximum conditional likelihood estimation for model training and L-BFGS for parameter estimation. Our methods achieve competitive performance for English, and outperform all previously reported dependency parsers for Chinese and Czech.

Related

• Headed-Span-Based Projective Dependency Parsing
• Global Greedy Dependency Parsing
• Neural Probabilistic Model for Non-projective MST Parsing
• A Bayesian Model for Generative Transition-based Dependency Parsing
• A* CCG Parsing with a Supertag and Dependency Factored Model