基于动态前缀微调的混合主导权响应生成
Mix-Initiative Response Generation with Dynamic Prefix Tuning
AI总结：
针对对话系统因不区分主导权导致的交叉污染问题，提出混合主导权动态前缀微调框架IDPT，通过解耦主导权因素并利用注意力机制动态调整选择，在监督和无监督设置下学习主导权感知前缀，在自动指标和人工评估上均优于基线。
摘要：
混合主导权是控制对话方向的关键因素之一。对于说话者而言，被动响应或主动引导会产生截然不同的回复。然而，大多数对话系统专注于训练一个整体的响应生成模型，不区分不同的主导权。这导致了交叉污染问题，模型会混淆不同的主导权并生成不恰当的回复。此外，获取大量主导权标签的人工标注可能成本高昂。为解决此问题，我们提出一种通用的混合主导权动态前缀微调框架（IDPT），将不同主导权与生成模型解耦，在监督和无监督设置下学习主导权感知前缀。具体而言，IDPT将主导权因素解耦到不同的前缀参数中，并利用注意力机制动态调整主导权的选择以指导生成。前缀参数可针对准确的主导权预测以及混合主导权响应生成进行微调。在两个公开对话数据集上的广泛实验表明，所提出的IDPT在自动指标和人工评估上均优于先前的基线。它还能在受控的主导权下生成恰当的响应。
英文摘要：
Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in both supervised and unsupervised settings. Specifically, IDPT decouples initiative factors into different prefix parameters and uses the attention mechanism to adjust the selection of initiatives in guiding generation dynamically. The prefix parameters can be tuned towards accurate initiative prediction as well as mix-initiative response generation. Extensive experiments on two public dialogue datasets show that the proposed IDPT outperforms previous baselines on both automatic metrics and human evaluations. It also manages to generate appropriate responses with manipulated initiatives.
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。
