ClusterPrompt: Cluster semantic enhanced prompt learning for new intent discovery
The discovery of new intent categories from user utterances is a crucial task in expanding agent skills. The key lies in how to efficiently solicit semantic evidence from utterances and properly transfer knowledge from existing intents to new intents. However, previous methods laid too much emphasis...
Saved in:
Main Authors: | LIANG, Jinggui, LIAO, Lizi |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8584 https://ink.library.smu.edu.sg/context/sis_research/article/9587/viewcontent/2023.findings_emnlp.702.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Prompting and evaluating large language models for proactive dialogues: Clarification, target-guided, and non-collaboration
by: DENG, Yang, et al.
Published: (2023) -
Voucher abuse detection with prompt-based fine-tuning on graph neural networks
by: WEN, Zhihao, et al.
Published: (2023) -
S-prompts learning with pre-trained transformers: An Occam's razor for domain incremental learning
by: WANG, Yabin, et al.
Published: (2022) -
How people prompt generative AI to create interactive VR scenes
by: AGHEL MANESH, Setareh, et al.
Published: (2024) -
Augmenting low-resource text classification with graph-grounded pre-training and prompting
by: WEN, Zhihao, et al.
Published: (2023)