TY - JOUR
T1 - Plain Template Insertion
T2 - Korean-Prompt-Based Engineering for Few-Shot Learners
AU - Seo, Jaehyung
AU - Moon, Hyeonseok
AU - Lee, Chanhee
AU - Eo, Sugyeong
AU - Park, Chanjun
AU - Kim, Jihoon
AU - Chun, Changwoo
AU - Lim, Heuiseok
N1 - Funding Information:
This work was supported in part by the Ministry of Science and ICT (MSIT), South Korea, under the ICT Creative Consilience Program Supervised by the Institute for Information & Communications Technology Planning & Evaluation (IITP) under Grant IITP-2022-2020-0-01819; in part by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education under Grant NRF-2021R1A6A1A03045425
Publisher Copyright:
© 2013 IEEE.
PY - 2022
Y1 - 2022
N2 - Prompt-based learning is a method used for language models to interpret natural language by remembering the prior knowledge acquired and the training objective. Recent prompt-based few-shot learners have achieved superior performance by alleviating the catastrophic forgetting that occurs in pretrained language models. Few-shot learning contributes towards solving the data scarcity problem, an enormous challenge in AI systems and a significant consideration in natural language processing research. In spite of the significance of few-shot learning, research on Korean language-based few-shot learning is insufficient, and whether the prompt-based approach is appropriate for the Korean language has not been thoroughly verified. As a step toward realizing a Korean-prompt-based few-shot learner, we attempt to apply prompt engineering to the Korean language understanding benchmark dataset and introduce plain template insertion to overcome data scarcity in a more practical few-shot setting. The contributions of this study are as follows: (1) presumably, this is the first study to apply prompt-based few-shot learning to Korean benchmark datasets. With 32 few-shot settings, it improves performance by +14.88, +29.04, and +1.81 in the natural language inference, semantic textual similarity, and topic classification tasks. (2) We present prompt engineering, which merely inserts a plain template and increases data efficiency without training example selection, augmentation, reformulation, and retrieval. (3) Our approach is robust to the Korean prompt's contextual information and sentence structure and is applicable to both hard- and soft-prompt.
AB - Prompt-based learning is a method used for language models to interpret natural language by remembering the prior knowledge acquired and the training objective. Recent prompt-based few-shot learners have achieved superior performance by alleviating the catastrophic forgetting that occurs in pretrained language models. Few-shot learning contributes towards solving the data scarcity problem, an enormous challenge in AI systems and a significant consideration in natural language processing research. In spite of the significance of few-shot learning, research on Korean language-based few-shot learning is insufficient, and whether the prompt-based approach is appropriate for the Korean language has not been thoroughly verified. As a step toward realizing a Korean-prompt-based few-shot learner, we attempt to apply prompt engineering to the Korean language understanding benchmark dataset and introduce plain template insertion to overcome data scarcity in a more practical few-shot setting. The contributions of this study are as follows: (1) presumably, this is the first study to apply prompt-based few-shot learning to Korean benchmark datasets. With 32 few-shot settings, it improves performance by +14.88, +29.04, and +1.81 in the natural language inference, semantic textual similarity, and topic classification tasks. (2) We present prompt engineering, which merely inserts a plain template and increases data efficiency without training example selection, augmentation, reformulation, and retrieval. (3) Our approach is robust to the Korean prompt's contextual information and sentence structure and is applicable to both hard- and soft-prompt.
KW - Korean language understanding
KW - Prompt-based learning
KW - few-shot
KW - language modeling
KW - natural language processing
UR - http://www.scopus.com/inward/record.url?scp=85139869065&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2022.3213027
DO - 10.1109/ACCESS.2022.3213027
M3 - Article
AN - SCOPUS:85139869065
SN - 2169-3536
VL - 10
SP - 107587
EP - 107597
JO - IEEE Access
JF - IEEE Access
ER -