UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Merging

Milan Straka, Jana Straková, Jan Hajic


Abstract
We present our contribution to the SIGMORPHON 2019 Shared Task: Crosslinguality and Context in Morphology, Task 2: contextual morphological analysis and lemmatization. We submitted a modification of the UDPipe 2.0, one of best-performing systems of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies and an overall winner of the The 2018 Shared Task on Extrinsic Parser Evaluation. As our first improvement, we use the pretrained contextualized embeddings (BERT) as additional inputs to the network; secondly, we use individual morphological features as regularization; and finally, we merge the selected corpora of the same language. In the lemmatization task, our system exceeds all the submitted systems by a wide margin with lemmatization accuracy 95.78 (second best was 95.00, third 94.46). In the morphological analysis, our system placed tightly second: our morphological analysis accuracy was 93.19, the winning system’s 93.23.
Anthology ID:
W19-4212
Volume:
Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Garrett Nicolai, Ryan Cotterell
Venue:
ACL
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
95–103
Language:
URL:
https://aclanthology.org/W19-4212
DOI:
10.18653/v1/W19-4212
Bibkey:
Cite (ACL):
Milan Straka, Jana Straková, and Jan Hajic. 2019. UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Merging. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 95–103, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Merging (Straka et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4212.pdf
Data
Universal Dependencies