Parsing Universal Dependencies without training

Héctor Martínez Alonso, Željko Agić, Barbara Plank, Anders Søgaard


Abstract
We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD. The parser has very few parameters and distinctly robust to domain change across languages.
Anthology ID:
E17-1022
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
230–240
Language:
URL:
https://aclanthology.org/E17-1022
DOI:
Bibkey:
Cite (ACL):
Héctor Martínez Alonso, Željko Agić, Barbara Plank, and Anders Søgaard. 2017. Parsing Universal Dependencies without training. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 230–240, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Parsing Universal Dependencies without training (Martínez Alonso et al., EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-1022.pdf
Code
 hectormartinez/ud_unsup_parser
Data
Universal Dependencies