Structured Training for Neural Network Transition-Based Parsing

Abstract

We present structured perceptron training for neural network transition-based dependency parsing. We learn the neural network representation using a gold corpus augmented by a large number of automatically parsed sentences. Given this fixed network representation, we learn a final layer using the structured perceptron with beam-search decoding. On the Penn Treebank, our parser reaches 94.26% unlabeled and 92.41% labeled attachment accuracy, which to our knowledge is the best accuracy on Stanford Dependencies to date. We also provide in-depth ablative analysis to determine which aspects of our model provide the largest gains in accuracy.

References in corpus (2)

• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Grammar as a Foreign Language

Cited by in corpus (8)

• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages
• Bi-directional Attention with Agreement for Dependency Parsing
• A Bayesian Model for Generative Transition-based Dependency Parsing
• Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
• A Simple LSTM model for Transition-based Dependency Parsing
• An empirical study for Vietnamese dependency parsing
• Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing