Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features

2020/07/09 by Ali Basirat, Joakim Nivre, Basirat, Ali +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2007.04686

openalex publication_date 2020/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We study the effect of rich supertag features in greedy transition-based dependency parsing. While previous studies have shown that sparse boolean features representing the 1-best supertag of a word can improve parsing accuracy, we show that we can get further improvements by adding a continuous vector representation of the entire supertag distribution for a word. In this way, we achieve the best results for greedy transition-based parsing with supertag features with 88.6% LAS and 90.9% UASon the English Penn Treebank converted to Stanford Dependencies.

Related

• Transition-based Parsing with Lighter Feed-Forward Networks
• Hexatagging: Projective Dependency Parsing as Tagging
• Global Greedy Dependency Parsing
• A Bayesian Model for Generative Transition-based Dependency Parsing
• Deep Contextualized Word Embeddings in Transition-Based and Graph-Based\n Dependency Parsing -- A Tale of Two Parsers Revisited