How (not) to train a dependency parser: The curious case of jackknifing part-of-speech taggers

Željko Agić, Natalie Schluter


Abstract
In dependency parsing, jackknifing taggers is indiscriminately used as a simple adaptation strategy. Here, we empirically evaluate when and how (not) to use jackknifing in parsing. On 26 languages, we reveal a preference that conflicts with, and surpasses the ubiquitous ten-folding. We show no clear benefits of tagging the training data in cross-lingual parsing.
Anthology ID:
P17-2107
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
679–684
Language:
URL:
https://aclanthology.org/P17-2107
DOI:
10.18653/v1/P17-2107
Bibkey:
Cite (ACL):
Željko Agić and Natalie Schluter. 2017. How (not) to train a dependency parser: The curious case of jackknifing part-of-speech taggers. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 679–684, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
How (not) to train a dependency parser: The curious case of jackknifing part-of-speech taggers (Agić & Schluter, ACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/P17-2107.pdf
Data
Universal Dependencies