Paper Info
Title
SyntaxNet Models for the CoNLL 2017 Shared Task.
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 Parseyu0027s Cousins models by 3.47% absolute Labeled Accuracy Score (LAS) across 52 treebanks.
Year
Venue
Field
2017
arXiv: Computation and Language
Computer science,Universal dependencies,Dependency grammar,Artificial intelligence,Natural language processing,Parsing,Machine learning
DocType
Volume
Citations 
Journal
abs/1703.04929
2
PageRank 
References 
Authors
0.37
9
13
Name
Order
Citations
PageRank
Chris Alberti12279.86
Daniel Andor21346.73
Ivan Bogatyy341.41
Michael Collins46788785.35
Dan Gillick525711.96
Lingpeng Kong623917.09
Terry Koo764229.39
Ji Ma8101.57
Mark Omernick920.37
Slav Petrov102405107.56
Chayut Thanapirom1120.37
Zora Tung1220.37
David J. Weiss1344619.11