Abstract
The Transformer model has been shown to outperform other neural seq2seq models in several character-level tasks. It is unclear, however, if the Transformer would benefit as much as other seq2seq models from data augmentation strategies in the low-resource setting. In this paper we explore strategies for data augmentation in the g2p task together with the Transformer model. Our results show that a relatively simple alignment-based strategy of identifying consistent input-output subsequences in grapheme-phoneme data coupled together with a subsequent splicing together of such pieces to generate hallucinated data works well in the low-resource setting, often delivering substantial performance improvement over a standard Transformer model.- Anthology ID:
- 2020.sigmorphon-1.21
- Volume:
- Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Garrett Nicolai, Kyle Gorman, Ryan Cotterell
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 184–188
- Language:
- URL:
- https://aclanthology.org/2020.sigmorphon-1.21
- DOI:
- 10.18653/v1/2020.sigmorphon-1.21
- Cite (ACL):
- Zach Ryan and Mans Hulden. 2020. Data Augmentation for Transformer-based G2P. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 184–188, Online. Association for Computational Linguistics.
- Cite (Informal):
- Data Augmentation for Transformer-based G2P (Ryan & Hulden, SIGMORPHON 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.sigmorphon-1.21.pdf