论文标题
依次的潜在知识选择，用于知识接地的对话
Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
论文作者
论文摘要
知识接地的对话是基于话语上下文和外部知识产生信息响应的任务。当我们专注于更好地建模多转化知识的对话中的知识选择时，我们提出了一个顺序的潜在变量模型，作为第一种方法。名为顺序知识变压器（SKT）的模型可以跟踪知识上的先验和后验分布。结果，它不仅可以减少知识选择的多样性所引起的歧义，而且还可以更好地利用响应信息来适当选择知识。我们的实验结果表明，所提出的模型提高了知识选择的准确性，并随后提高了发音生成的性能。我们在Wikipedia巫师（Dinan等，2019）上实现了最新的最新表现，成为最大规模和最具挑战性的基准之一。我们进一步验证了在另一个基于知识的对话HOLL-E数据集中模型对现有对话方法的有效性（Moghe等，2018）。
Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge; as a result, it can not only reduce the ambiguity caused from the diversity in knowledge selection of conversation but also better leverage the response information for proper choice of knowledge. Our experimental results show that the proposed model improves the knowledge selection accuracy and subsequently the performance of utterance generation. We achieve the new state-of-the-art performance on Wizard of Wikipedia (Dinan et al., 2019) as one of the most large-scale and challenging benchmarks. We further validate the effectiveness of our model over existing conversation methods in another knowledge-based dialogue Holl-E dataset (Moghe et al., 2018).
