Learning Bidirectional Morphological Inflection like Humans

Akiyo Fukatsu, Yuto Harada, Yohei Oseki


Abstract
For nearly the past forty years, there has been discussion regarding whether symbolic representations are involved in morphological inflection, a debate commonly known as the Past Tense Debate. The previous literature has extensively explored whether neural models, which do not use symbolic representations can process morphological inflection like humans. However, current research interest has shifted towards whether neural models can acquire morphological inflection like humans. In this paper, we trained neural models, the recurrent neural network (RNN) with attention and the transformer, and a symbolic model, the Minimal Generalization Learner (MGL), under a human-like learning environment. Evaluating the models from the perspective of language acquisition, we found that while the transformer and the MGL exhibited some human-like characteristics, the RNN with attention did not demonstrate human-like behavior across all the evaluation metrics considered in this study. Furthermore, none of the models accurately inflected verbs in the same manner as humans in terms of morphological inflection direction. These results suggest that these models fall short as cognitive models of morphological inflection.
Anthology ID:
2024.lrec-main.895
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
10249–10262
Language:
URL:
https://aclanthology.org/2024.lrec-main.895
DOI:
Bibkey:
Cite (ACL):
Akiyo Fukatsu, Yuto Harada, and Yohei Oseki. 2024. Learning Bidirectional Morphological Inflection like Humans. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10249–10262, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Learning Bidirectional Morphological Inflection like Humans (Fukatsu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.895.pdf