Structured Training for Neural Network Transition-Based Parsing

2015/06/19 by David J. Weiss, Weiss, David, Chris Alberti +5 · 9 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1506.06158

openalex publication_date 2015/06/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Incremental Parsing with Minimal Features Using Bi-Directional LSTM
• Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
• Mapping the Course for Prompt-based Structured Prediction
• Dependency Parsing as Head Selection
• Bi-directional Attention with Agreement for Dependency Parsing
• Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning
• A Simple LSTM model for Transition-based Dependency Parsing
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Recent Trends in Deep Learning Based Natural Language Processing
• A Fast, Compact, Accurate Model for Language Identification of Codemixed Text

Related

• Transition-Based Dependency Parsing using Perceptron Learner
• Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training
• On the Challenges of Fully Incremental Neural Dependency Parsing
• Lock-Free Parallel Perceptron for Graph-based Dependency Parsing
• Dependency Parsing with LSTMs: An Empirical Evaluation