IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks

Anders Björkelund, Agnieszka Falenska, Xiang Yu, Jonas Kuhn


Abstract
This paper presents the IMS contribution to the CoNLL 2017 Shared Task. In the preprocessing step we employed a CRF POS/morphological tagger and a neural tagger predicting supertags. On some languages, we also applied word segmentation with the CRF tagger and sentence segmentation with a perceptron-based parser. For parsing we took an ensemble approach by blending multiple instances of three parsers with very different architectures. Our system achieved the third place overall and the second place for the surprise languages.
Anthology ID:
K17-3004
Volume:
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–51
Language:
URL:
https://aclanthology.org/K17-3004
DOI:
10.18653/v1/K17-3004
Bibkey:
Cite (ACL):
Anders Björkelund, Agnieszka Falenska, Xiang Yu, and Jonas Kuhn. 2017. IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 40–51, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks (Björkelund et al., CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3004.pdf