Response Generation with Context-Aware Prompt Learning

Abstract

Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue styles. However, tailoring the language models while fully utilizing prior knowledge in large pre-trained models remains a challenge. In this paper, we present a novel approach for pre-trained dialogue modeling that casts the dialogue generation problem as a prompt-learning task. Instead of fine-tuning on limited dialogue data, our approach, DialogPrompt, learns continuous prompt embeddings optimized for dialogue contexts, which appropriately elicit knowledge from the large pre-trained model. To encourage the model to better utilize the prompt embeddings, the prompt encoders are designed to be dynamically generated based on the dialogue context. Experiments on popular conversation datasets show that our approach significantly outperforms the fine-tuning baseline and the generic prompt-learning methods. Furthermore, human evaluations strongly support the superiority of DialogPrompt in regard to response generation quality.

References in corpus (8)

• Decoupled Weight Decay Regularization
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
• Prefix-Tuning: Optimizing Continuous Prompts for Generation
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
• AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
• Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation