Generalizing Morphological Inflection Systems to Unseen Lemmas

Changbing Yang, Ruixin (Ray) Yang, Garrett Nicolai, Miikka Silfverberg


Abstract
This paper presents experiments on morphological inflection using data from the SIGMORPHON-UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection. We present a transformer inflection system, which enriches the standard transformer architecture with reverse positional encoding and type embeddings. We further apply data hallucination and lemma copying to augment training data. We train models using a two-stage procedure: (1) We first train on the augmented training data using standard backpropagation and teacher forcing. (2) We then continue training with a variant of the scheduled sampling algorithm dubbed student forcing. Our system delivers competitive performance under the small and large data conditions on the shared task datasets.
Anthology ID:
2022.sigmorphon-1.23
Volume:
Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
July
Year:
2022
Address:
Seattle, Washington
Editors:
Garrett Nicolai, Eleanor Chodroff
Venue:
SIGMORPHON
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
226–235
Language:
URL:
https://aclanthology.org/2022.sigmorphon-1.23
DOI:
10.18653/v1/2022.sigmorphon-1.23
Bibkey:
Cite (ACL):
Changbing Yang, Ruixin (Ray) Yang, Garrett Nicolai, and Miikka Silfverberg. 2022. Generalizing Morphological Inflection Systems to Unseen Lemmas. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 226–235, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Generalizing Morphological Inflection Systems to Unseen Lemmas (Yang et al., SIGMORPHON 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigmorphon-1.23.pdf