An Ensembled Encoder-Decoder System for Interlinear Glossed Text
Edith Coates · 2023
This paper presents a submission to Track 1 of the 2023 SIGMORPHON shared task on interlinear glossed text (IGT) (Ginn et al., 2023).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).We describe the system's ensembled sequence-to-sequence approach, perform experiments, and share the submission's test-set accuracy.We also discuss future areas of research in low-resource token classification methods for IGT.