Prompt Tuning Techniques for Chinese Idiom Recommendation

Chinese idioms pose significant challenges in natural language processing (NLP) due to their complex, non-compositional nature and frequent embedded cultural and historical meanings. This study investigates prompt tuning techniques for Chinese idiom recommendation, exploring multiple-choice (MC) pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Shun-Ming Wang, I-Fang Su, Yu-Chi Chung
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10965689/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712614547914752
author Shun-Ming Wang
I-Fang Su
Yu-Chi Chung
author_facet Shun-Ming Wang
I-Fang Su
Yu-Chi Chung
author_sort Shun-Ming Wang
collection DOAJ
description Chinese idioms pose significant challenges in natural language processing (NLP) due to their complex, non-compositional nature and frequent embedded cultural and historical meanings. This study investigates prompt tuning techniques for Chinese idiom recommendation, exploring multiple-choice (MC) prompts, binary classification (BC) prompts, and prompt ensembling strategies. We also introduce an innovative dynamic candidate sampling strategy (DCSS) technique designed to mitigate the overfitting issues commonly encountered with prompt tuning methods on Chinese idiom datasets. Our experimental results demonstrate that prompt tuning combined with ensembling methods significantly improves model performance across multiple datasets. The proposed methods outperform the state-of-the-art (SOTA) methods while maintaining training and inference efficiency. Moreover, we show that prompt tuning can effectively be generalized for other NLP tasks, such as sentiment analysis.
format Article
id doaj-art-4e0400a2428d4123b90eff664daef39a
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4e0400a2428d4123b90eff664daef39a2025-08-20T03:14:13ZengIEEEIEEE Access2169-35362025-01-0113680376805110.1109/ACCESS.2025.356118810965689Prompt Tuning Techniques for Chinese Idiom RecommendationShun-Ming Wang0I-Fang Su1https://orcid.org/0000-0002-6785-5906Yu-Chi Chung2https://orcid.org/0000-0001-7488-9998Department of Industrial Engineering and Management, National Kaohsiung University of Science and Technology, Kaohsiung City, Sanmin, TaiwanDepartment of Computer Science and Information Engineering, National University of Tainan, Tainan City, West Central District, TaiwanDepartment of Industrial Engineering and Management, National Kaohsiung University of Science and Technology, Kaohsiung City, Sanmin, TaiwanChinese idioms pose significant challenges in natural language processing (NLP) due to their complex, non-compositional nature and frequent embedded cultural and historical meanings. This study investigates prompt tuning techniques for Chinese idiom recommendation, exploring multiple-choice (MC) prompts, binary classification (BC) prompts, and prompt ensembling strategies. We also introduce an innovative dynamic candidate sampling strategy (DCSS) technique designed to mitigate the overfitting issues commonly encountered with prompt tuning methods on Chinese idiom datasets. Our experimental results demonstrate that prompt tuning combined with ensembling methods significantly improves model performance across multiple datasets. The proposed methods outperform the state-of-the-art (SOTA) methods while maintaining training and inference efficiency. Moreover, we show that prompt tuning can effectively be generalized for other NLP tasks, such as sentiment analysis.https://ieeexplore.ieee.org/document/10965689/Chinese idiom recommendationdeep learningprompt engineering/tuningpre-trained language modelNLP
spellingShingle Shun-Ming Wang
I-Fang Su
Yu-Chi Chung
Prompt Tuning Techniques for Chinese Idiom Recommendation
IEEE Access
Chinese idiom recommendation
deep learning
prompt engineering/tuning
pre-trained language model
NLP
title Prompt Tuning Techniques for Chinese Idiom Recommendation
title_full Prompt Tuning Techniques for Chinese Idiom Recommendation
title_fullStr Prompt Tuning Techniques for Chinese Idiom Recommendation
title_full_unstemmed Prompt Tuning Techniques for Chinese Idiom Recommendation
title_short Prompt Tuning Techniques for Chinese Idiom Recommendation
title_sort prompt tuning techniques for chinese idiom recommendation
topic Chinese idiom recommendation
deep learning
prompt engineering/tuning
pre-trained language model
NLP
url https://ieeexplore.ieee.org/document/10965689/
work_keys_str_mv AT shunmingwang prompttuningtechniquesforchineseidiomrecommendation
AT ifangsu prompttuningtechniquesforchineseidiomrecommendation
AT yuchichung prompttuningtechniquesforchineseidiomrecommendation