CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems
By Fei Mi, Yitong Li, Yasheng Wang, Xin Jiang, Qun Liu. 2021
46 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yi-Ting Yeh
- Shikib Mehri
- Maxine Eskénazi
- Minlie Huang
- Chujie Zheng
- Prakhar Gupta
- Jeffrey P. Bigham
- Cathy Jiao
Citations in the corpus
- Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation (2021, result): “We compared several representative pre-trained models to be used as the backbone models, which are also popularly adopted in previous works of dialog generation (Mi et al., 2021; Shuster et al., 2021).”
- InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning (2022, methodology): “Similarly, BERT-type pretrained models have been used for language understanding in TOD tasks (Wu et al., 2020a; Mi et al., 2021b).”
- DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (2022, unknown): “There has also been progress in using natural language prompts and instructions to control models (Gupta et al., 2022b; Mi et al., 2022; Chung et al., 2022), but our work extends this by providing fine-grained semantic control through guidelines over open domain response generation.”