论文标题
Blackbox世代的后控制
Posterior Control of Blackbox Generation
论文作者
论文摘要
文本生成通常需要遵守特定任务规则的高精度输出。通过现成的深度学习模型，这种细粒度的控制很难执行。在这项工作中，我们考虑通过通过结构化的潜在方法学到的离散控制状态来增强神经产生模型。在此公式下，特定于任务的知识可以通过一系列有效地训练为模型的丰富的后部约束来编码。这种方法使用户可以基于先验知识的内部模型决策，而无需牺牲神经生成模型的代表性。实验考虑了这种方法在文本生成中的应用。我们发现，这种方法比标准基准有所改善，同时也提供细粒度的控制。
Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. Under this formulation, task-specific knowledge can be encoded through a range of rich, posterior constraints that are effectively trained into the model. This approach allows users to ground internal model decisions based on prior knowledge, without sacrificing the representational power of neural generative models. Experiments consider applications of this approach for text generation. We find that this method improves over standard benchmarks, while also providing fine-grained control.
