基于人设自适应注意力机制的个性化对话生成
Personalized Dialogue Generation with Persona-Adaptive Attention
AI总结：
本文提出基于人设自适应注意力（PAA）的对话生成框架，通过自适应整合上下文与人设权重并应用动态掩码机制，在低资源下表现优异。
摘要：
基于人设的对话系统旨在根据历史上下文和预定义人设生成一致的回复。与传统对话生成不同，基于人设的对话需要同时考虑对话上下文和人设，这对连贯训练提出了挑战。具体而言，这需要在上下文和人设之间实现微妙的权重平衡。为了实现这一点，在本文中，我们提出了一个具有人设自适应注意力（Persona-Adaptive Attention, PAA）的有效框架，该框架通过我们设计的注意力自适应地整合来自人设和上下文信息的权重。此外，PAA应用了动态掩码机制，不仅能够丢弃上下文和人设中的冗余信息，还能作为正则化机制来避免过拟合。实验结果证明了所提出的PAA框架在自动评估和人工评估中相较于强基线的优越性。此外，与在全数据设置下训练的模型相比，所提出的PAA方法在低资源情况下表现同样出色，仅使用20%到30%的数据即可达到与在全数据设置下训练的更大模型相似的结果。为了充分验证我们设计的有效性，我们设计了几个以不同方式处理加权信息的变体，展示了我们加权和掩码设计的必要性与充分性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
