TY  - JOUR
T1  - Prompt Tuning For Korean Aspect-Based Sentiment Analysis
AU  - Kim, Bong-Su 
AU  - Choi, Seung-Ho 
AU  - Park, Si-hyun 
AU  - Wang, Jun-Ho 
AU  - Kim, Ji-Yoon 
AU  - Jeon, Hyun-Kyu 
AU  - Jang, Jung-Hoon 
JO  - Journal of KIISE, JOK
PY  - 2024
DA  - 2024/1/14
DO  - 10.5626/JOK.2024.51.12.1043
KW  - Aspect-Based Sentiment Analysis
KW  - prompt tuning
KW  - Few-Shot Learning
KW  - dependency parsing
AB  - Aspect-based sentiment analysis examines how emotions in text relate to specific aspects, such as product characteristics or service features. This paper presents a comprehensive methodology for applying prompt tuning techniques to multi-task token labeling challenges using aspect-based sentiment analysis data. The methodology includes a pipeline for identifying emotion expression domains, which generalizes the token labeling problem into a sequence labeling problem. It also suggests selecting templates to classify separated sequences based on aspects and emotions, and expanding label words to align with the dataset’s characteristics, thus optimizing the model's performance. Finally, the paper provides several experimental results and analyses for the aspect-based sentiment analysis task in a few-shot setting. The constructed data and baseline model are available on AIHUB. (www.aihub.or.kr).