The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy

Éric de La Clergerie, Benoît Sagot, Djamé Seddah

[How to correct problems with metadata yourself]

Abstract
We present the ParisNLP entry at the UD CoNLL 2017 parsing shared task. In addition to the UDpipe models provided, we built our own data-driven tokenization models, sentence segmenter and lexicon-based morphological analyzers. All of these were used with a range of different parsing models (neural or not, feature-rich or not, transition or graph-based, etc.) and the best combination for each language was selected. Unfortunately, a glitch in the shared task’s Matrix led our model selector to run generic, weakly lexicalized models, tailored for surprise languages, instead of our dataset-specific models. Because of this #ParsingTragedy, we officially ranked 27th, whereas our real models finally unofficially ranked 6th.
Anthology ID:
K17-3026
Volume:
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Jan Hajič, Dan Zeman
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
243–252
Language:
URL:
https://aclanthology.org/K17-3026
DOI:
10.18653/v1/K17-3026
Bibkey:
Cite (ACL):
Éric de La Clergerie, Benoît Sagot, and Djamé Seddah. 2017. The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 243–252, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy (de La Clergerie et al., CoNLL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/K17-3026.pdf
Data
Universal Dependencies
PDF Search