Prompt tuning on Graph-Augmented Low-Resource text classification

• Main Authors: WEN, Zhihao, FANG, Yuan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Accuracy; graph; Ink; low-resource learning Oils; Paints; pre-training; prompt; Task analysis; Text categorization; Text classification; Tuning; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/9275; https://ink.library.smu.edu.sg/context/sis_research/article/10275/viewcontent/Prompt_tuning_GALR_tc_av.pdf
• Institution: Singapore Management University

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with no or few labeled samples, presents a serio...