CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog Systems


  • Fei Mi Huawei Noah’s Ark Lab
  • Yasheng Wang Huawei Noah’s Ark Lab
  • Yitong Li Huawei Technologies Co., Ltd.



Speech & Natural Language Processing (SNLP)


As the labeling cost for different modules in task-oriented dialog (ToD) systems is high, a major challenge is to learn different tasks with the least amount of labeled data. Recently, pre-trained language models (PLMs) have shown promising results for few-shot learning in ToD. To better utilize the power of PLMs, this paper proposes Comprehensive Instruction (CINS) that exploits PLMs with extra task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD, ie. intent classification, dialog state tracking, and natural language generation. A sequence-to-sequence model (T5) is adopted to solve these three tasks in a unified framework. Extensive experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data. Empirical results demonstrate that the proposed CINS approach consistently improves techniques that finetune PLMs with raw input or short prompt.




How to Cite

Mi, F., Wang, Y., & Li, Y. (2022). CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog Systems. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11076-11084.



AAAI Technical Track on Speech and Natural Language Processing