Approximation-Aware Dependency Parsing by Belief Propagation
| Autor: | Mark Dredze, Matthew R. Gormley, Jason Eisner |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
FOS: Computer and information sciences
Linguistics and Language Computer science Posterior probability computer.software_genre Belief propagation Machine Learning (cs.LG) Artificial Intelligence Dependency grammar Differentiable function CRFS Computer Science - Computation and Language Parsing Training set business.industry Communication Pattern recognition Backpropagation Computer Science Applications Human-Computer Interaction Computer Science - Learning Artificial intelligence business Computation and Language (cs.CL) computer Algorithm |
| Zdroj: | Transactions of the Association for Computational Linguistics. 3:489-501 |
| ISSN: | 2307-387X |
| Popis: | We show how to train the fast dependency parser of Smith and Eisner (2008) for improved accuracy. This parser can consider higher-order interactions among edges while retaining O( n3) runtime. It outputs the parse with maximum expected recall—but for speed, this expectation is taken under a posterior distribution that is constructed only approximately, using loopy belief propagation through structured factors. We show how to adjust the model parameters to compensate for the errors introduced by this approximation, by following the gradient of the actual loss on training data. We find this gradient by back-propagation. That is, we treat the entire parser (approximations and all) as a differentiable circuit, as others have done for loopy CRFs (Domke, 2010; Stoyanov et al., 2011; Domke, 2011; Stoyanov and Eisner, 2012). The resulting parser obtains higher accuracy with fewer iterations of belief propagation than one trained by conditional log-likelihood. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|