University of Illinois Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection

Marc Canby, Aidana Karipbayeva, Bryan Lunt, Sahand Mozaffari, Charlotte Yoder, Julia Hockenmaier


Abstract
The objective of this shared task is to produce an inflected form of a word, given its lemma and a set of tags describing the attributes of the desired form. In this paper, we describe a transformer-based model that uses a bidirectional decoder to perform this task, and evaluate its performance on the 90 languages and 18 language families used in this task.
Anthology ID:
2020.sigmorphon-1.15
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:
137–145
Language:
URL:
https://aclanthology.org/2020.sigmorphon-1.15
DOI:
10.18653/v1/2020.sigmorphon-1.15
Bibkey:
Cite (ACL):
Marc Canby, Aidana Karipbayeva, Bryan Lunt, Sahand Mozaffari, Charlotte Yoder, and Julia Hockenmaier. 2020. University of Illinois 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 137–145, Online. Association for Computational Linguistics.
Cite (Informal):
University of Illinois Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection (Canby et al., SIGMORPHON 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.sigmorphon-1.15.pdf