Neural models are being widely applied for text summarization, including headline generation, and are typically trained using a set of document-headline pairs. In a large document set, documents can usually be grouped into various topics, and documents within a certain topic may exhibit specific summarization patterns. Most existing neural models, however, have not taken the topic information of documents into consideration. This paper categorizes documents into multiple topics, since documents within the same topic have similar content and share similar summarization patterns. By taking advantage of document topic information, this study proposes a topic-sensitive neural headline generation model (TopicNHG). It is evaluated on a real-world dataset, large scale Chinese short text summarization dataset. Experimental results show that it outperforms several baseline systems on each topic and achieves comparable performance with the state-of-the-art system. This indicates that TopicNHG can generate more accurate headlines guided by document topics.

神经模型已广泛应用于文本摘要，包括标题生成，并且通常使用一组文档标题对进行训练。在大型文档集中，通常可以将文档分为不同的主题，并且某个主题内的文档可以表现出特定的摘要模式。但是，大多数现有的神经模型都没有考虑文档的主题信息。本文将文档分为多个主题，因为同一主题内的文档具有相似的内容并且共享相似的摘要模式。通过利用文档主题信息的优势，本研究提出了主题敏感的神经标题生成模型（TopicNHG）。在真实数据集，大规模中文短文本摘要数据集上进行评估。实验结果表明，它在每个主题上的性能均优于几个基准系统，并具有与最新系统相当的性能。这表明TopicNHG可以根据文档主题生成更准确的标题。