论文标题
模板指导的文本生成，用于任务对话
Template Guided Text Generation for Task-Oriented Dialogue
论文作者
论文摘要
诸如Google Assistant，Amazon Alexa和Apple Siri之类的虚拟助手使用户可以使用自然语言在网络上与大量服务和API进行交互。在这项工作中，我们使用大量API的单个独立模型研究了两种自然语言产生（NLG）的方法。首先，我们提出了一种架构引导的方法，该方法在描述自然语言的API方面的一代条件。我们的第二种方法研究了少数模板的使用，即在数量上线性地生长，以传达API的语义。为了生成任意插槽组合的话语，首先将一些简单的模板连接起来，以使语义上正确但可能是不连贯且不语法的话语。随后采用了预训练的语言模型将其改写为连贯的自然声音文本。通过自动指标和人类评估，我们表明我们的方法改善了强大的基准，对跨域输入是可靠的，并且显示出提高的样品效率。
Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language Generation (NLG) using a single domain-independent model across a large number of APIs. First, we propose a schema-guided approach which conditions the generation on a schema describing the API in natural language. Our second method investigates the use of a small number of templates, growing linearly in number of slots, to convey the semantics of the API. To generate utterances for an arbitrary slot combination, a few simple templates are first concatenated to give a semantically correct, but possibly incoherent and ungrammatical utterance. A pre-trained language model is subsequently employed to rewrite it into coherent, natural sounding text. Through automatic metrics and human evaluation, we show that our method improves over strong baselines, is robust to out-of-domain inputs and shows improved sample efficiency.
