Template Oriented Text Summarization via Knowledge Graph

People are flooded with massive semi-structured and unstructured texts in their daily work life. The fast-paced lifestyle has forced us to get more focused information from these large amounts of text more quickly. So people urgently need a technology that can automatically extract abstracts from text. The traditional extractive automatic abstract method can only extract keywords or key sentences. Although the current popular sequence-to-sequence extraction methods have greatly improved compared with the traditional methods, they cannot be combined with the background information to obtain higher level abstraction. Therefore, we propose a method based on knowledge graph technology to automatically extract abstract texts. This method can not only obtain higher-level extraction from the text, but also can select template and question and answer to obtain a personalized abstract. We experimented on the CNN DAILYMAIL dataset. The results show that the abstract obtained by this method can reflect more textual information, and more in line with human reading habits, and can achieve personalized extraction, and can obtain close to the best ROUGE index results.