Improving Coverage and Runtime Complexity for Exact Inference in Non-Projective Transition-Based Dependency Parsers.
Tianze ShiCarlos Gómez-RodríguezLillian LeePublished in: NAACL-HLT (2) (2018)
Keyphrases
- exact inference
- graphical models
- approximate inference
- dependency parser
- bayesian networks
- probabilistic inference
- dependency parsing
- belief propagation
- belief networks
- worst case
- dynamic bayesian networks
- conditional random fields
- approximation algorithms
- computational complexity
- co occurrence
- probabilistic model
- message passing
- feature vectors
- variational methods
- image segmentation