Abstract
This paper presents my submission to Track 1 of the 2023 SIGMORPHON shared task on interlinear glossed text (IGT). There are a wide amount of techniques for building and training IGT models (see Moeller and Hulden, 2018; McMillan-Major, 2020; Zhao et al., 2020). I describe my ensembled sequence-to-sequence approach, perform experiments, and share my submission’s test-set accuracy. I also discuss future areas of research in low-resource token classification methods for IGT.- Anthology ID:
- 2023.sigmorphon-1.23
- Volume:
- Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Garrett Nicolai, Eleanor Chodroff, Frederic Mailhot, Çağrı Çöltekin
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 217–221
- Language:
- URL:
- https://aclanthology.org/2023.sigmorphon-1.23
- DOI:
- 10.18653/v1/2023.sigmorphon-1.23
- Cite (ACL):
- Edith Coates. 2023. An Ensembled Encoder-Decoder System for Interlinear Glossed Text. In Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 217–221, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- An Ensembled Encoder-Decoder System for Interlinear Glossed Text (Coates, SIGMORPHON 2023)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2023.sigmorphon-1.23.pdf