@article{ART002899651},
author={Kim Euhee},
title={A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2022},
volume={27},
number={11},
pages={39-46},
doi={10.9708/jksci.2022.27.11.039}

TY - JOUR
AU - Kim Euhee
TI - A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations
JO - Journal of The Korea Society of Computer and Information
PY - 2022
VL - 27
IS - 11
PB - The Korean Society Of Computer And Information
SP - 39
EP - 46
SN - 1598-849X
AB - In this paper, we propose a multi-task model that can simultaneously predict general-purpose tasks such as part-of-speech tagging, lemmatization, and dependency parsing using the UD Korean Kaist v2.3 corpus. The proposed model thus applies the self-attention technique of the BERT model and the graph-based Biaffine attention technique by fine-tuning the multilingual BERT and the two Korean-specific BERTs such as KR-BERT and KoBERT. The performances of the proposed model are compared and analyzed using the multilingual version of BERT and the two Korean-specific BERT language models.
KW - Universal Dependency;Multilingual BERT;KR-BERT;KoBERT;Fine-tuning;Pre-training
DO - 10.9708/jksci.2022.27.11.039
ER -

Kim Euhee. (2022). A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations. Journal of The Korea Society of Computer and Information, 27(11), 39-46.

Kim Euhee. 2022, "A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations", Journal of The Korea Society of Computer and Information, vol.27, no.11 pp.39-46. Available from: doi:10.9708/jksci.2022.27.11.039

Kim Euhee "A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations" Journal of The Korea Society of Computer and Information 27.11 pp.39-46 (2022) : 39.

Kim Euhee. A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations. 2022; 27(11), 39-46. Available from: doi:10.9708/jksci.2022.27.11.039

Kim Euhee. "A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations" Journal of The Korea Society of Computer and Information 27, no.11 (2022) : 39-46.doi: 10.9708/jksci.2022.27.11.039

Kim Euhee. A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations. Journal of The Korea Society of Computer and Information, 27(11), 39-46. doi: 10.9708/jksci.2022.27.11.039

Kim Euhee. A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations. Journal of The Korea Society of Computer and Information. 2022; 27(11) 39-46. doi: 10.9708/jksci.2022.27.11.039

Kim Euhee. A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations. 2022; 27(11), 39-46. Available from: doi:10.9708/jksci.2022.27.11.039

Kim Euhee. "A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations" Journal of The Korea Society of Computer and Information 27, no.11 (2022) : 39-46.doi: 10.9708/jksci.2022.27.11.039