Jeong, C., Schmitz, D., Kakolu Ramarao, A., Stein, A. S., & Tang, K. (To appearTo appear). Linear Discriminative Learning: a competitive non-neural baseline for morphological inflection. Proceedings of the 20th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology. https://aclanthology.org/2023.sigmorphon-1.16.pdf.
@inproceedings{JeongSchmitzKakoluRSteinTang_LDL_SIGMORPHON_2023,
author = {Jeong, Cheonkam and Schmitz, Dominic and {Kakolu Ramarao}, Akhilesh and {Stein}, Anna Sophia and Tang, Kevin},
title = {Linear {D}iscriminative {L}earning: a competitive non-neural baseline for morphological inflection},
booktitle = {Proceedings of the 20th {SIGMORPHON} Workshop on {C}omputational {R}esearch in {P}honetics, {P}honology, and {M}orphology},
year = {{To appear}},
publisher = {Association for Computational Linguistics},
note = {https://aclanthology.org/2023.sigmorphon-1.16.pdf},
file = {jeongetal-sigmorphon-2023.pdf}
}
This paper presents our submission to the SIGMORPHON 2023 task 2 of Cognitively Plausible Morphophonological Generalization in Korean. We implemented both Linear Discriminative Learning and Transformer models and found that the Linear Discriminative Learning model trained on a combination of corpus and experimental data showed the best performance with the overall accuracy of around 83 percent. We found that the best model must be trained on both corpus data and the experimental data of one particular participant. Our examination of speaker-variability and speaker-specific information did not explain why a particular participant combined well with the corpus data. We recommend Linear Discriminative Learning models as a future non-neural baseline system, owning to its training speed, accuracy, model interpretability and cognitive plausibility. In order to improve the model performance, we suggest using bigger data and/or performing data augmentation and incorporating speaker- and item-specifics considerably.