UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task

Milan Straka


Abstract
UDPipe is a trainable pipeline which performs sentence segmentation, tokenization, POS tagging, lemmatization and dependency parsing. We present a prototype for UDPipe 2.0 and evaluate it in the CoNLL 2018 UD Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, which employs three metrics for submission ranking. Out of 26 participants, the prototype placed first in the MLAS ranking, third in the LAS ranking and third in the BLEX ranking. In extrinsic parser evaluation EPE 2018, the system ranked first in the overall score.
Anthology ID:
K18-2020
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:
197–207
Language:
URL:
https://aclanthology.org/K18-2020
DOI:
10.18653/v1/K18-2020
Bibkey:
Cite (ACL):
Milan Straka. 2018. UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 197–207, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task (Straka, CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-2020.pdf
Data
Universal Dependencies