Response Generation with Context-Aware Prompt Learning
This work addresses the problem of efficient dialogue modeling for AI systems, offering a novel approach that is incremental in improving response generation quality.
The paper tackles the challenge of tailoring pre-trained language models for dialogue generation without extensive fine-tuning by introducing DialogPrompt, a method that learns context-aware prompt embeddings to elicit knowledge from the model, resulting in significant performance improvements over baselines on conversation datasets.
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.