论文标题
与内容计划的插件食谱生成
Plug-and-Play Recipe Generation with Content Planning
论文作者
论文摘要
最近的预训练的语言模型显示出在产生流利和逼真的自然语言文本方面有希望的能力。但是，使用全球内容计划生成多句话文本一直是一个长期存在的研究问题。当前的受控文本生成方法几乎无法解决此问题，因为它们通常在单个已知控制属性上条件。在这项研究中，我们提出了一个低成本但有效的框架，该框架明确地模拟了生成的文本的全球内容计划。具体而言，它以插件方式优化了自然语言序列和全球内容计划的联合分布。我们对良好的配方1M+基准进行了广泛的实验。自动和人类评估都验证了我们的模型是否在食谱生成任务上实现了最先进的表现
Recent pre-trained language models have shown promising capabilities in generating fluent and realistic natural language text. However, generating multi-sentence text with global content planning has been a long-existing research question. Current approaches for controlled text generation can hardly address this issue, as they usually condition on single known control attributes. In this study, we propose a low-cost yet effective framework which explicitly models the global content plan of the generated text. Specifically, it optimizes the joint distribution of the natural language sequence and the global content plan in a plug-and-play manner. We conduct extensive experiments on the well-established Recipe1M+ benchmark. Both automatic and human evaluations verify that our model achieves the state-of-the-art performance on the task of recipe generation
