Episode-based Prompt Learning for Any-shot Intent Detection
Published in NLPCC 2023 Oral, 2023
Recommended citation: Sun, Pengfei, et al. "Episode-Based Prompt Learning for Any-Shot Intent Detection." CCF International Conference on Natural Language Processing and Chinese Computing. Cham: Springer Nature Switzerland, 2023.
TL;DR Episode-based Prompt Learning recasts intent detection as prompted sentence-pair classification and simulates varying label availability during training, supporting both unseen intents and intents with only a few labeled examples.
Pengfei Sun, Dingjie Song (equal contribution), Yawen Ouyang, Zhen Wu, Xinyu Dai
Recommended citation: Sun, Pengfei, et al. “Episode-Based Prompt Learning for Any-Shot Intent Detection.” CCF International Conference on Natural Language Processing and Chinese Computing. Cham: Springer Nature Switzerland, 2023.