The UniMelb Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection

Andreas Scherbakov


Abstract
The paper describes the University of Melbourne’s submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection. Our team submitted three systems in total, two neural and one non-neural. Our analysis of systems’ performance shows positive effects of newly introduced data hallucination technique that we employed in one of neural systems, especially in low-resource scenarios. A non-neural system based on observed inflection patterns shows optimistic results even in its simple implementation (>75% accuracy for 50% of languages). With possible improvement within the same modeling principle, accuracy might grow to values above 90%.
Anthology ID:
2020.sigmorphon-1.20
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:
177–183
Language:
URL:
https://aclanthology.org/2020.sigmorphon-1.20
DOI:
10.18653/v1/2020.sigmorphon-1.20
Bibkey:
Cite (ACL):
Andreas Scherbakov. 2020. The UniMelb Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 177–183, Online. Association for Computational Linguistics.
Cite (Informal):
The UniMelb Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection (Scherbakov, SIGMORPHON 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.sigmorphon-1.20.pdf