Dialogue systems need to produce responses that realize multiple types of dialogue acts (DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for dialogue were trained on large parallel corpora that map from a domain-specific DA and its semantic attributes to an output utterance. Recent work shows that pretrained language models (LLMs) offer new possibilities for controllable NLG using prompt-based learning. Here we develop a novel few-shot overgenerate-and-rank approach that achieves the controlled generation of DAs. We compare eight few-shot prompt styles that include a novel method of generating from textual pseudo-references using a textual style transfer approach. We develop six automatic ranking functions that identify outputs with both the correct DA and high semantic accuracy at generation time. We test our approach on three domains and four LLMs. To our knowledge, this is the first work on NLG for dialogue that automatically ranks outputs using both DA and attribute accuracy. For completeness, we compare our results to fine-tuned few-shot models trained with 5 to 100 instances per DA. Our results show that several prompt settings achieve perfect DA accuracy, and near perfect semantic accuracy (99.81%) and perform better than few-shot fine-tuning.

翻译：对话系统需要生成实现多种对话行为且语义保真度高的回应。过去，对话自然语言生成器依赖大规模并行语料库训练，将领域特定的对话行为及其语义属性映射为输出语句。近期研究表明，预训练语言模型通过提示学习为可控自然语言生成提供了新可能。本文提出一种新颖的少样本过生成-排序方法，实现了对对话行为的可控生成。我们比较了八种少样本提示风格，其中包括一种使用文本风格迁移方法从文本伪参考中生成的新型方法。我们开发了六种自动排序函数，在生成阶段即可识别出兼具正确对话行为与高语义准确性的输出。该方法在三个领域和四种预训练语言模型上进行了测试。据我们所知，这是首个在对话自然语言生成中同时基于对话行为与属性准确性对输出进行自动排序的研究。为完整性起见，我们将结果与每个对话行为使用5至100个实例微调的少样本模型进行对比。结果表明，多种提示设置可实现完美的对话行为准确性，接近完美的语义准确性（99.81%），且性能优于少样本微调方法。