Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In order to produce a coherent flow of text, we explore two forms of intersentential relations in a paragraph: one is a human-created linguistical relation that forms a structure (e.g., discourse tree) and the other is a relation from latent representation learned from the sentences themselves. Our two proposed models incorporate each form of relations into document-level language models: the former is a supervised model that jointly learns a language model as well as discourse relation prediction, and the latter is an unsupervised model that is hierarchically conditioned by a recurrent neural network (RNN) over the latent information. Our proposed models with both forms of relations outperform the baselines in partially conditioned paragraph generation task. Our codes and data are publicly available.

研究探索通过人工创造的语言关系和句子本身学习到的潜在关系将两种形式的 intersentential relations 整合到文档级语言模型中，其中一个为监督模型，另一个为无监督模型，其实现部分条件下的段落生成任务效果优于基准方法。

用语言和隐藏关系建模自然段中的连贯流