论文标题
分类器是可控文本的更好专家
Classifiers are Better Experts for Controllable Text Generation
论文作者
论文摘要
本文提出了一种简单的方法，用于使用自由形式分类器（即CAIF采样），基于加权逻辑来控制文本生成。使用任意的文本分类器，我们将语言模型逻辑的一小部分调整为指导文本生成，以指向或远离分类器预测。我们试验了避免毒性和情感控制任务，并表明该方法在PPL和DEXPERT上明显胜过PPLM，GEDI和DEXPERTS，并基于基于生成的文本的外部分类器的PPL和任务准确性指标。此外，与其他方法相比，它更容易实施和调整，并且限制和要求较少。
This paper proposes a simple method for controllable text generation based on weighting logits with a free-form classifier, namely CAIF sampling. Using an arbitrary text classifier, we adjust a small part of a language model's logits and guide text generation towards or away from classifier prediction. We experimented with toxicity avoidance and sentiment control tasks and showed that the proposed method significantly outperforms recent PPLM, GeDi, and DExperts on PPL and task accuracy metrics based on the external classifier of generated texts. In addition, compared to other approaches, it is easier to implement and tune and has significantly fewer restrictions and requirements.
