论文标题
Turngpt：一种基于变压器的语言模型，用于预测口语对话中的转折点
TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog
论文作者
论文摘要
众所周知，句法和务实的完整性对于转弯预测很重要，但是到目前为止，转弯的机器学习模型已经以有限的方式使用了此类语言信息。在本文中，我们介绍了Turngpt，这是一种基于变压器的语言模型，用于预测口语对话框中的转弯。该模型已在各种书面和口语对话框数据集上进行了培训和评估。我们表明，该模型的表现优于先前工作中使用的两个基准。我们还报告了一项消融研究以及注意力和梯度分析，该研究表明该模型能够利用对话框上下文和务实的完整性来进行转向预测。最后，我们不仅探讨了该模型的潜力，而且还探讨了投影旋转完成的潜力。
Syntactic and pragmatic completeness is known to be important for turn-taking prediction, but so far machine learning models of turn-taking have used such linguistic information in a limited way. In this paper, we introduce TurnGPT, a transformer-based language model for predicting turn-shifts in spoken dialog. The model has been trained and evaluated on a variety of written and spoken dialog datasets. We show that the model outperforms two baselines used in prior work. We also report on an ablation study, as well as attention and gradient analyses, which show that the model is able to utilize the dialog context and pragmatic completeness for turn-taking prediction. Finally, we explore the model's potential in not only detecting, but also projecting, turn-completions.
