Sequential Graph Dependency Parser

2019/05/27 by Sean Welleck, Kyunghyun Cho, Welleck, Sean +1
Biochemistry, Genetics and Molecular Biology · Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Bioinformatics #Natural Language Processing Techniques #Software Engineering Research

paper · pdf · doi:10.48550/arxiv.1905.10930

openalex publication_date 2019/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The proposed transition-based method successfully parses near the state of the art on both projective and non-projective languages, without assuming a certain parsing order.

Citations

• Order Matters: Sequence to sequence for sets
• Learning Deep Generative Models of Graphs
• Insertion-based Decoding with automatically Inferred Generation Order
• Insertion Transformer: Flexible Sequence Generation via Insertion\n Operations
• A Reduction of Imitation Learning and Structured Prediction to No-Regret\n Online Learning

Related

• Combining (second-order) graph-based and headed-span-based projective dependency parsing
• Headed-Span-Based Projective Dependency Parsing
• Global Greedy Dependency Parsing
• Semi-supervised Autoencoding Projective Dependency Parsing
• Dependency Graph Parsing as Sequence Labeling