响应条件的交替预测（英文版）

英文标题：Response-conditioned Turn-taking Prediction中文摘要：本文提出一种模型，该模型将对话历史和下一个讲话者想要说的内容作为条件来预测对话的结束，比基线模型在各种指标上的表现更好。该模型可作为一个增量响应排名器，在各种场景中得到应用。英文摘要：Previous approaches to turn-taking and response generation in conversationalsystems have treated it as a two-stage process: First, the end of a turn isdetected (based on conversation history), then the system generates anappropriate response. Humans, however, do not take the turn just because it islikely, but also consider whether what they want to say