CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems

@inproceedings{Mi2022CINSCI,
  title={CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems},
  author={Fei Mi and Yitong Li and Yasheng Wang and Xin Jiang and Qun Liu},
  booktitle={AAAI},
  year={2022}
}
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… 
Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
TLDR
An end-to-end chatbot named the Few-Shot Bot is created, which automatically selects the most appropriate conversational skill, queries different knowledge bases or the internet, and uses the retrieved knowledge to generate a human-like response, all using only few dialogue examples per skill.
Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
TLDR
This work introduces I NSTRUCT D IAL, an instruction tuning framework for dialogue, which consists of a repository of 48 diverse dialogue tasks in a unified text-to-text format created from 59 openly available dialogue datasets, and reveals that it enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection, and even better performance in a few-shot setting.
Continual Prompt Tuning for Dialog State Tracking
TLDR
This paper presents Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks, and proposes several techniques to transfer knowledge from preceding tasks and a memory-guided technique to transferknowledge from subsequent tasks.
Description-Driven Task-Oriented Dialog Modeling
TLDR
This paper proposes that schemata should be modified by replacing names or notations entirely with natural language descriptions, and shows that a language description-driven system exhibits better understanding of task specifications, higher performance on state tracking, improved data efficiency, and effective zero-shot transfer to unseen tasks.
Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation
TLDR
The potential of prompt-based methods in few-shot learning for grounded dialog generation for GDG is demonstrated and directions of improvement for future work are provided.
LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework
TLDR
This work proposes LMTurk, a novel approach that treats few-shot learners as crowdsourcing workers, and shows that the resulting annotations can be utilized to train models that solve the task well and are small enough to be deployable in practical scenarios.
Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking
TLDR
It is hypothesized that dialogue summaries are essentially unstructured dialogue states; hence, it is proposed to reformulate dialogue state tracking as a dialogue summarization problem, and the method DS2 outperforms previous works on few-shot DST in MultiWoZ 2.0 and 2.1.
Toxicity Detection with Generative Prompt-based Inference
TLDR
This work explores the generative variant of zero-shot prompt-based toxicity detection with comprehensive trials on prompt engineering and highlights the strengths of its generative classification approach both quantitatively and qualitatively.
LMTurk: Few-Shot Learners as Crowdsourcing Workers
TLDR
This work proposes LMTurk, a novel approach that treats few-shot learners as crowdsourcing workers built upon PLMs as workers and shows that the resulting annotations can be utilized to train models that solve the task well and are small enough to be deployable in practical scenarios.

References

SHOWING 1-10 OF 48 REFERENCES
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
TLDR
A self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model is proposed and a new text augmentation technique (GradAug) is proposed to better train the Student by replacing non-crucial tokens using a masked language model.
Few-shot Natural Language Generation for Task-Oriented Dialog
TLDR
FewshotWOZ is presented, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems, and the proposed SC-GPT model significantly outperforms existing methods, measured by various automatic metrics and human evaluations.
SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model
TLDR
A new method SOLOIST is presented, which uses transfer learning to efficiently build task-oriented dialog systems at scale using a Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model.
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
TLDR
This paper proposes a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm, and defines a set of meta tasks, and directly incorporates the objective of adapting to new low-resource NLG tasks into the meta- learning optimization process.
Making Pre-trained Language Models Better Few-shot Learners
TLDR
The LM-BFF approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning.
Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
TLDR
This work proposes a method called ARPER (Adaptively Regularized Prioritized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on Elastic Weight Consolidation.
A Simple Language Model for Task-Oriented Dialogue
TLDR
SimpleTOD is a simple approach to task-oriented dialogue that uses a single causal language model trained on all sub-tasks recast as a single sequence prediction problem, which allows it to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2.
Language Models are Few-Shot Learners
TLDR
GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
Natural Instructions: Benchmarking Generalization to New Tasks from Natural Language Instructions
TLDR
This work uses the existing NLP datasets and the instructions used to crowdsource them to create NATURALINSTRUCTIONS, a dataset of instructions and task-specific input/output data that indicates that the existing models indeed benefit from instructions and hence, show improved generalization to new tasks.
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
TLDR
This work explores the idea of learning prompts by gradient descent—either fine-tuning prompts taken from previous work, or starting from random initialization, showing that the implicit factual knowledge in language models was previously underestimated.
...
...