CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems
This work addresses the problem of reducing labeling effort for developers of task-oriented dialog systems, but it is incremental as it builds on existing prompting methods.
The paper tackles the high labeling cost in task-oriented dialog systems by proposing Comprehensive Instruction (CINS), a method that uses extra task-specific instructions with pre-trained language models for few-shot learning, resulting in consistent improvements over baseline techniques in intent classification, dialog state tracking, and natural language generation tasks.
As labeling cost for different modules in task-oriented dialog (ToD) systems is high, a major challenge in practice is to learn different tasks with the least amount of labeled data. Recently, prompting methods over 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, i.e. 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 prompts.