Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
arXiv:2110.08118
Abstract
Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language models (LMs) fine-tuned on large conversational datasets. Training these models is expensive, both in terms of computational resources and time, and it is hard to keep them up to date with new conversational skills. A simple yet unexplored solution is prompt-based few-shot learning (Brown et al. 2020) which does not require gradient-based fine-tuning but instead uses a few examples in the LM context as the only source of learning. In this paper, we explore prompt-based few-shot learning in dialogue tasks. We benchmark LMs of different sizes in nine response generation tasks, which include four knowledge-grounded tasks, a task-oriented generations task, three open-chat tasks, and controlled stylistic generation, and five conversational parsing tasks, which include dialogue state tracking, graph path generation, persona information extraction, document retrieval, and internet query generation. The current largest released LM (GPT-J-6B) using prompt-based few-shot learning, and thus requiring no training, achieves competitive performance to fully trained state-of-the-art models. Moreover, we propose a novel prompt-based few-shot classifier, that also does not require any fine-tuning, to select the most appropriate prompt given a dialogue history. Finally, by combining the power of prompt-based few-shot learning and a Skill Selector, we create an end-to-end chatbot named the Few-Shot Bot (FSB), 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.
References in corpus (28)
- Sequence to Sequence Learning with Neural Networks
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Longformer: The Long-Document Transformer
- YFCC100M: The New Data in Multimedia Research
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
- Towards a Human-like Open-Domain Chatbot
- Making Pre-trained Language Models Better Few-shot Learners
- Multimodal Few-Shot Learning with Frozen Language Models
- Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
- Calibrate Before Use: Improving Few-Shot Performance of Language Models
- Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems
- BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
- Controlling Style in Generated Dialogue
- Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation
- On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression
- STAR: A Schema-Guided Dialog Dataset for Transfer Learning
- Attention over Parameters for Dialogue Systems
- Getting To Know You: User Attribute Extraction from Dialogues
- Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
- Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
- Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
- SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
- Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning
- Assessing Political Prudence of Open-domain Chatbots
- Greenformer: Factorization Toolkit for Efficient Deep Neural Networks
- Zero-Shot Dialogue State Tracking via Cross-Task Transfer