Cross-lingual Character-Level Neural Morphological Tagging

Ryan Cotterell, Georg Heigold


Abstract
Even for common NLP tasks, sufficient supervision is not available in many languages – morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones.
Anthology ID:
D17-1078
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
748–759
Language:
URL:
https://aclanthology.org/D17-1078
DOI:
10.18653/v1/D17-1078
Bibkey:
Cite (ACL):
Ryan Cotterell and Georg Heigold. 2017. Cross-lingual Character-Level Neural Morphological Tagging. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 748–759, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Cross-lingual Character-Level Neural Morphological Tagging (Cotterell & Heigold, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1078.pdf
Data
Universal Dependencies