论文标题
通过基于KNN的复合记忆进行对话增强变压器
Augmenting Transformers with KNN-Based Composite Memory for Dialogue
论文作者
论文摘要
各种机器学习任务可以受益于访问不同模式的外部信息，例如文本和图像。最近的工作集中在学习体系结构上，具有能够存储这些知识的大记忆。我们建议使用基于KNN的信息获取（KIF）模块的增强生成变压器神经网络。每个KIF模块都会学习一个读取操作，以访问固定的外部知识。我们将这些模块应用于生成对话框建模，这是一项具有挑战性的任务，必须灵活地检索和合并信息以维护对话的主题和流动。我们通过确定Wikipedia，图像和人文编写的对话框的知识渊博但引人入胜的对话所需的相关知识来证明我们的方法的有效性，并表明利用此检索到的信息可以改善通过自动和人类评估来衡量的模型性能。
Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialog modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge required for knowledgeable but engaging dialog from Wikipedia, images, and human-written dialog utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.
