论文标题
以任务为导向的对话框的自然语言生成很少
Few-shot Natural Language Generation for Task-Oriented Dialog
论文作者
论文摘要
作为面向任务的对话系统的关键组成部分，自然语言生成（NLG）模块将以语义形式表示的对话框转换为自然语言的响应。传统模板或统计模型的成功通常取决于大量注释的数据，这对于新域而言是不可行的。因此，NLG系统在实际应用程序中使用有限的标记数据进行概括是关键的。为此，我们介绍了很少的Shotwoz，这是第一个模拟以任务为导向的对话框系统中的少数图学习设置的NLG基准。此外，我们开发了SC-GPT模型。它已在大量注释的NLG语料库中进行了预训练，可以获得可控的生成能力，并且仅使用少数特定领域的标签进行微调以适应新的域。关于Lighshotwoz和大型多域WOZ数据集的实验表明，所提出的SC-GPT明显胜过现有方法，该方法通过各种自动指标和人类评估来衡量。
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications. To this end, we present FewShotWoz, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develop the SC-GPT model. It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains. Experiments on FewShotWoz and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods, measured by various automatic metrics and human evaluations.
