通过内容规划生成即插即用食谱
Plug-and-Play Recipe Generation with Content Planning
摘要:
最近的预训练语言模型在生成流畅和逼真的自然语言文本方面表现出了很好的能力。然而,生成多句子的文本与全球内容规划一直是一个长期存在的研究问题。当前的控制文本生成方法很难解决这个问题,因为它们通常以单个已知的控件属性为条件。在这项研究中,我们提出了一个低成本但有效的框架,明确建模的全球内容计划生成的文本。具体而言,它以即插即用的方式优化了自然语言序列和全局内容计划的联合分发。我们在成熟的Recipe1M+基准上进行了广泛的实验。自动和人工评估都验证了我们的模型在配方生成任务上达到了最先进的性能
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。