SyntaxNet Models for the CoNLL 2017 Shared Task

2017/03/15 by Alberti, Chris, Andor, Daniel, Bogatyy, Ivan +10
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1703.04929

Abstract

We describe a baseline dependency parsing system for the CoNLL2017 Shared Task. This system, which we call "ParseySaurus," uses the DRAGNN framework [Kong et al, 2017] to combine transition-based recurrent parsing and tagging with character-based word representations. On the v1.3 Universal Dependencies Treebanks, the new system outpeforms the publicly available, state-of-the-art "Parsey's Cousins" models by 3.47% absolute Labeled Accuracy Score (LAS) across 52 treebanks.

Related

• Universal Dependency Parsing from Scratch
• 82 Treebanks, 34 Models: Universal Dependency Parsing with\n Multi-Treebank Models
• The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task
• Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation
• Technical notes: Syntax-aware Representation Learning With Pointer Networks