Efficient Cross-Task Prompt Tuning for Few-Shot Conversational Emotion Recognition
This work addresses the need for sample and computational efficiency in emotion recognition for conversational AI, though it is incremental as it builds on existing prompt tuning methods.
The authors tackled the problem of few-shot conversational emotion recognition by proposing Cross-Task Prompt Tuning (CTPT), a derivative-free optimization method that leverages cross-task knowledge to improve learning efficiency, achieving superior results on few-shot and zero-shot scenarios across five datasets.
Emotion Recognition in Conversation (ERC) has been widely studied due to its importance in developing emotion-aware empathetic machines. The rise of pre-trained language models (PLMs) has further pushed the limit of ERC performance. However, most recent works on ERC using PLMs are heavily data-driven, and requires fine-tuning the entire PLMs. To improve both sample and computational efficiency, we propose a derivative-free optimization method called Cross-Task Prompt Tuning (CTPT) for few-shot conversational emotion recognition. Unlike existing methods that learn independent knowledge from individual tasks, CTPT leverages sharable cross-task knowledge by exploiting external knowledge from other source tasks to improve learning performance under the few-shot setting. Moreover, CTPT only needs to optimize a vector under the low intrinsic dimensionality without gradient, which is highly parameter-efficient compared with existing approaches. Experiments on five different contextual conversation datasets demonstrate that our CTPT method has superior results on both few-shot scenarios and zero-shot transfers.