Neural Transition-based String Transduction for Limited-Resource Setting in Morphology

Peter Makarov, Simon Clematide


Abstract
We present a neural transition-based model that uses a simple set of edit actions (copy, delete, insert) for morphological transduction tasks such as inflection generation, lemmatization, and reinflection. In a large-scale evaluation on four datasets and dozens of languages, our approach consistently outperforms state-of-the-art systems on low and medium training-set sizes and is competitive in the high-resource setting. Learning to apply a generic copy action enables our approach to generalize quickly from a few data points. We successfully leverage minimum risk training to compensate for the weaknesses of MLE parameter learning and neutralize the negative effects of training a pipeline with a separate character aligner.
Anthology ID:
C18-1008
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
83–93
Language:
URL:
https://aclanthology.org/C18-1008
DOI:
Bibkey:
Cite (ACL):
Peter Makarov and Simon Clematide. 2018. Neural Transition-based String Transduction for Limited-Resource Setting in Morphology. In Proceedings of the 27th International Conference on Computational Linguistics, pages 83–93, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Neural Transition-based String Transduction for Limited-Resource Setting in Morphology (Makarov & Clematide, COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/C18-1008.pdf
Code
 ZurichNLP/coling2018-neural-transition-based-morphology
Data
CELEX