论文标题
PCAE：用于可控文本的插入式有条件自动编码器的框架
PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation
论文作者
论文摘要
如今，可控制的文字生成已经迈出了巨大的一步。然而，现有方法要么受到一次性模式的限制，要么不足以在每个一代阶段接受多个条件。我们为可控文本生成（PCAE）提出了一个模型 - 反应式插件条件自动编码器，朝着灵活和半监视的文本生成。我们的框架是“插件”，其中部分参数要在预训练的模型中进行微调（少于一半）。对PCAE的成功至关重要的是提议的广播标签融合网络，用于将全球潜在代码导航到指定的本地和限制空间。局部潜在先验井的可视化证实了所提出模型的隐藏空间中的主要奉献精神。此外，基于RNN的五个相关一代任务（从2个条件到10条条件）进行的广泛实验均在基于RNN的BART [26]的自动编码器上都揭示了PCAE的高能力，这使得可以高度操纵，语法上的多样化和时间节省时间，并具有最低标记的样品。我们将在https://github.com/imkett/pcae上发布代码。
Controllable text generation has taken a gigantic step forward these days. Yet existing methods are either constrained in a one-off pattern or not efficient enough for receiving multiple conditions at every generation stage. We propose a model-agnostic framework Plug-in Conditional Auto-Encoder for Controllable Text Generation (PCAE) towards flexible and semi-supervised text generation. Our framework is "plug-and-play" with partial parameters to be fine-tuned in the pre-trained model (less than a half). Crucial to the success of PCAE is the proposed broadcasting label fusion network for navigating the global latent code to a specified local and confined space. Visualization of the local latent prior well confirms the primary devotion in hidden space of the proposed model. Moreover, extensive experiments across five related generation tasks (from 2 conditions up to 10 conditions) on both RNN- based and pre-trained BART [26] based auto-encoders reveal the high capability of PCAE, which enables generation that is highly manipulable, syntactically diverse and time-saving with minimum labeled samples. We will release our code at https://github.com/ImKeTT/pcae.
