Natural Language Generation (NLG) for task-oriented dialogue systems focuses
on communicating specific content accurately, fluently, and coherently. While
these attributes are crucial for a successful dialogue, it is also desirable to
simultaneously accomplish specific stylistic goals, such as response length,
point-of-view, descriptiveness, sentiment, formality, and empathy. In this
work, we focus on stylistic control and evaluation for schema-guided NLG, with
joint goals of achieving both semantic and stylistic control. We experiment in
detail with various controlled generation methods for large pretrained language
models: specifically, conditional training, guided fine-tuning, and guided
decoding. We discuss their advantages and limitations, and evaluate them with a
broad range of automatic and human evaluation metrics. Our results show that
while high style accuracy and semantic correctness are easier to achieve for
more lexically-defined styles with conditional training, stylistic control is
also achievable for more semantically complex styles using discriminator-based
guided decoding methods. The results also suggest that methods that are more
scalable (with less hyper-parameters tuning) and that disentangle content
generation and stylistic variations are more effective at achieving semantic
correctness and style accuracy.

本研究着重于架构引导的自然语言生成中的风格控制和评估，旨在同时实现语义和风格控制，通过条件训练、引导微调和引导解码等各种控制生成方法的实验来评估其优缺点，并用广泛的自动和人工评估指标来评估，结果表明，使用判别器引导解码更适合处理风格较为语义复杂的任务，同时这种方法也更加可扩展，效果更好。