论文标题
独奏者：通过转移学习和机器教学进行大规模构建任务机器人
SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
论文作者
论文摘要
我们提出了一个新的方法独奏者，该独奏者使用转移学习和机器教学来大规模构建任务机器人。我们使用基于变压器的自动回归语言模型参数化经典模块化的面向任务对话框系统，该模型将不同的对话框模块归为单个神经模型。我们预先培训，在异构对话COLPORA上，这是一个由任务接收的响应生成模型，该模型可以生成基于用户目标和现实世界知识以完成任务完成的对话框响应。可以通过机器教学进行一些特定于任务的对话框来有效地适应预训练的模型，以完成新的任务，在该对话中，培训样本是由与系统互动的人类教师生成的。实验表明，（i）独奏者在面向任务的对话框基准（包括CAMREST676和MULTIWOZ）上创建了新的最先进的对话。 （ii）在少数拍摄的微调设置中，独奏者的表现明显优于现有方法，并且（iii）使用机器教学可大大降低微调的标签成本。预训练的模型和代码可在https://aka.ms/soloist上找到。
We present a new method SOLOIST that uses transfer learning and machine teaching to build task bots at scale. We parameterize classical modular task-oriented dialog systems using a Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model. We pre-train, on heterogeneous dialog corpora, a task-grounded response generation model, which can generate dialog responses grounded in user goals and real-world knowledge for task completion. The pre-trained model can be efficiently adapted to accomplish new tasks with a handful of task-specific dialogs via machine teaching, where training samples are generated by human teachers interacting with the system. Experiments show that (i) SOLOIST creates new state-of-the-art on well-studied task-oriented dialog benchmarks, including CamRest676 and MultiWOZ; (ii) in the few-shot fine-tuning settings, SOLOIST significantly outperforms existing methods, and (iii) the use of machine teaching substantially reduces the labeling cost of fine-tuning. The pre-trained models and codes are available at https://aka.ms/soloist.
