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:
- 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)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/C18-1008.pdf
- Code
- ZurichNLP/coling2018-neural-transition-based-morphology
- Data
- CELEX