论文标题
神经叙事产生的解码方法
Decoding Methods for Neural Narrative Generation
论文作者
论文摘要
叙事生成是一项开放式的NLP任务，其中模型在给定提示的情况下生成故事。该任务类似于聊天机器人的神经反应生成。但是，尽管这些任务之间有相似之处，但响应产生的创新通常并不适用于叙事产生。我们的目的是通过应用和评估在神经反应产生神经叙事生成中的解码方法中的进步来弥合这一差距。特别是，我们采用GPT-2并在核采样阈值和各种解码超参数（特别是最大的共同信息）上进行消融，并通过自动和人类评估来分析多个标准的结果。我们发现（1）核采样通常是最佳的，阈值在0.7至0.9之间； （2）最大的共同信息目标可以提高生成的故事的质量； （3）已建立的自动指标与任何定性指标对人类叙事质量的判断没有很好的关系。
Narrative generation is an open-ended NLP task in which a model generates a story given a prompt. The task is similar to neural response generation for chatbots; however, innovations in response generation are often not applied to narrative generation, despite the similarity between these tasks. We aim to bridge this gap by applying and evaluating advances in decoding methods for neural response generation to neural narrative generation. In particular, we employ GPT-2 and perform ablations across nucleus sampling thresholds and diverse decoding hyperparameters -- specifically, maximum mutual information -- analyzing results over multiple criteria with automatic and human evaluation. We find that (1) nucleus sampling is generally best with thresholds between 0.7 and 0.9; (2) a maximum mutual information objective can improve the quality of generated stories; and (3) established automatic metrics do not correlate well with human judgments of narrative quality on any qualitative metric.
