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 Alberti | 1 | 227 | 9.86 |
Daniel Andor | 2 | 134 | 6.73 |
Ivan Bogatyy | 3 | 4 | 1.41 |
Michael Collins | 4 | 6788 | 785.35 |
Dan Gillick | 5 | 257 | 11.96 |
Lingpeng Kong | 6 | 239 | 17.09 |
Terry Koo | 7 | 642 | 29.39 |
Ji Ma | 8 | 10 | 1.57 |
Mark Omernick | 9 | 2 | 0.37 |
Slav Petrov | 10 | 2405 | 107.56 |
Chayut Thanapirom | 11 | 2 | 0.37 |
Zora Tung | 12 | 2 | 0.37 |
David J. Weiss | 13 | 446 | 19.11 |