Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training

2020/10/10 by Xinyu Wang, Kewei Tu, Wang, Xinyu +1 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2010.05003

openalex publication_date 2020/10/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose second-order graph-based neural dependency parsing using message passing and end-to-end neural networks. We empirically show that our approaches match the accuracy of very recent state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing. We also empirically show the advantage of second-order parsing over first-order parsing and observe that the usefulness of the head-selection structured constraint vanishes when using BERT embedding.

Citations

• Efficient Second-Order TreeCRF for Neural Dependency Parsing

Cited by

• Sparse Fuzzy Attention for Structured Sentiment Analysis

Related

• Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
• Structured Training for Neural Network Transition-Based Parsing
• Transferring Neural Potentials For High Order Dependency Parsing
• A Higher-Order Semantic Dependency Parser
• Second-Order Unsupervised Neural Dependency Parsing