research
∙
06/08/2023
Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
We consider the task of few-shot intent detection, which involves traini...
share
research
∙
05/12/2023
Asymmetric feature interaction for interpreting model predictions
In natural language processing (NLP), deep neural networks (DNNs) could ...
research
∙
05/25/2022
New Intent Discovery with Pre-training and Contrastive Learning
New intent discovery aims to uncover novel intent categories from user u...
research
∙
05/15/2022
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization
It is challenging to train a good intent classifier for a task-oriented ...
research
∙
09/13/2021