Zhenghong Hao

Semi-Supervised Clustering with Contrastive Learning for Discovering New Intents

2022 · arXiv (Cornell University)

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most scenarios …

Hierarchical Prompt Tuning for Few-Shot Multi-Task Learning

2023

Prompt tuning has enhanced the performance of Pre-trained Language Models for multi-task learning in few-shot scenarios. However, existing studies fail to consider that the prompts among different layers in Transformer are different due to the …