Universal Dependency Parsing with a General Transition-Based DAG Parser

Daniel Hershcovich, Omri Abend, Ari Rappoport


Abstract
This paper presents our experiments with applying TUPA to the CoNLL 2018 UD shared task. TUPA is a general neural transition-based DAG parser, which we use to present the first experiments on recovering enhanced dependencies as part of the general parsing task. TUPA was designed for parsing UCCA, a cross-linguistic semantic annotation scheme, exhibiting reentrancy, discontinuity and non-terminal nodes. By converting UD trees and graphs to a UCCA-like DAG format, we train TUPA almost without modification on the UD parsing task. The generic nature of our approach lends itself naturally to multitask learning.
Anthology ID:
K18-2010
Volume:
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Daniel Zeman, Jan Hajič
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
103–112
Language:
URL:
https://aclanthology.org/K18-2010
DOI:
10.18653/v1/K18-2010
Bibkey:
Cite (ACL):
Daniel Hershcovich, Omri Abend, and Ari Rappoport. 2018. Universal Dependency Parsing with a General Transition-Based DAG Parser. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 103–112, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Universal Dependency Parsing with a General Transition-Based DAG Parser (Hershcovich et al., CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-2010.pdf
Poster:
 K18-2010.Poster.pdf
Code
 CoNLL-UD-2018/HUJI
Data
Universal Dependencies