Korean Morphological Analysis with Tied Sequence-to-Sequence Multi-Task Model

Hyun-Je Song, Seong-Bae Park


Abstract
Korean morphological analysis has been considered as a sequence of morpheme processing and POS tagging. Thus, a pipeline model of the tasks has been adopted widely by previous studies. However, the model has a problem that it cannot utilize interactions among the tasks. This paper formulates Korean morphological analysis as a combination of the tasks and presents a tied sequence-to-sequence multi-task model for training the two tasks simultaneously without any explicit regularization. The experiments prove the proposed model achieves the state-of-the-art performance.
Anthology ID:
D19-1150
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1436–1441
Language:
URL:
https://aclanthology.org/D19-1150
DOI:
10.18653/v1/D19-1150
Bibkey:
Cite (ACL):
Hyun-Je Song and Seong-Bae Park. 2019. Korean Morphological Analysis with Tied Sequence-to-Sequence Multi-Task Model. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1436–1441, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Korean Morphological Analysis with Tied Sequence-to-Sequence Multi-Task Model (Song & Park, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1150.pdf