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

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.

Accepted to AACL 2020. 7 pages

References in corpus (2)

• On the Convergence of Adam and Beyond
• Efficient Second-Order TreeCRF for Neural Dependency Parsing

Cited by in corpus (5)

• Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
• Automated Concatenation of Embeddings for Structured Prediction
• Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
• Sparse Fuzzy Attention for Structured Sentiment Analysis
• Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings