Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States
TL
TL;DR
This paper proposes a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models with the introduction of error states in local training.
Abstract
Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach achieves 93.61% accuracy for transition-based dependency parsing in English.
References39 items
1
Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training
2
Structured Training for Neural Network Transition-Based Parsing
3
Enforcing Structural Diversity in Cube-pruned Dependency Parsing
4
Training Deterministic Parsers with Non-Deterministic Oracles
5