Persona-based dialogue systems aim to generate consistent responses based on historical context and predefined persona. Unlike conventional dialogue generation, the persona-based dialogue needs to consider both dialogue context and persona, posing a challenge for coherent training. Specifically, this requires a delicate weight balance between context and persona. To achieve that, in this paper, we propose an effective framework with Persona-Adaptive Attention (PAA), which adaptively integrates the weights from the persona and context information via our designed attention. In addition, a dynamic masking mechanism is applied to the PAA to not only drop redundant information in context and persona but also serve as a regularization mechanism to avoid overfitting. Experimental results demonstrate the superiority of the proposed PAA framework compared to the strong baselines in both automatic and human evaluation. Moreover, the proposed PAA approach can perform equivalently well in a low-resource regime compared to models trained in a full-data setting, which achieve a similar result with only 20% to 30% of data compared to the larger models trained in the full-data setting. To fully exploit the effectiveness of our design, we designed several variants for handling the weighted information in different ways, showing the necessity and sufficiency of our weighting and masking designs.

翻译：人物驱动的对话系统旨在基于历史上下文和预设人物生成一致的回复。与传统对话生成不同，人物驱动对话需同时考虑对话上下文和人物特征，这对模型的一致性训练提出了挑战。具体而言，这要求模型在上下文与人物特征之间实现精细的权重平衡。为此，本文提出了一种基于人物自适应注意力（PAA）的高效框架，该框架通过我们设计的注意力机制自适应整合人物特征与上下文信息的权重。此外，我们在PAA中应用了动态掩码机制，不仅能丢弃上下文和人物特征中的冗余信息，还能作为正则化手段防止过拟合。实验结果表明，在自动评估和人工评估中，所提出的PAA框架相较于强基线方法均展现出显著优势。值得注意的是，该PAA方法在低资源场景下的性能与全数据训练模型相当——仅需全数据训练大模型所用数据的20%至30%即可达到相似结果。为充分验证设计的有效性，我们设计了多种以不同方式处理加权信息的变体模型，证明了加权与掩码设计的必要性和充分性。