论文标题
针对任务导向的对话系统的半监督知识培训的预训练
Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
论文作者
论文摘要
神经方法的最新进展极大地改善了以任务为导向的对话（TOD）系统，这些对话（TOD）可以帮助用户实现目标。但是，此类系统依赖于昂贵的手动标记的对话框，这些对话框在实际情况下不可用。在本文中，我们介绍了Seretod 2022 Challenge的曲目2，这是在大型现实世界中的中国TOD数据集Mobilecs上建立半监督和加强TOD系统的第一个挑战。我们构建了一个知识接地的对话模型，以制定对话框历史记录和本地KB作为输入，并预测系统响应。我们在标记和未标记的数据上进行半监督预训练。我们的系统在自动评估和人类相互作用中都获得了第一名，尤其是与第二名相比，BLEU（+7.64）和成功（+7.64）和成功（+13.6 \％）的第一名。
Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals. However, such systems rely on costly manually labeled dialogs which are not available in practical scenarios. In this paper, we present our models for Track 2 of the SereTOD 2022 challenge, which is the first challenge of building semi-supervised and reinforced TOD systems on a large-scale real-world Chinese TOD dataset MobileCS. We build a knowledge-grounded dialog model to formulate dialog history and local KB as input and predict the system response. And we perform semi-supervised pre-training both on the labeled and unlabeled data. Our system achieves the first place both in the automatic evaluation and human interaction, especially with higher BLEU (+7.64) and Success (+13.6\%) than the second place.
