Abstract generation method based on planning mechanism and knowledge graph guidance

Abstract

The invention provides an abstract generation method based on a planning mechanism and knowledge graph guidance. The method comprises the steps: directly taking a knowledge graph as the input of a model, extracting attention features from the uninterrupted global semantic features of the knowledge graph in an abstract decoding process, and maintaining the semantic consistency of the context of anabstract; compared with a text generation model adopting a graph neural network as an encoder, the method has the advantages that entity information covered by each sentence segment in the abstract isannotated in a supervised manner, so that a planning mechanism module of the training model can capture semantic features of a generated text before the sentence segments are generated; therefore, the sub-graphs of the knowledge graph are further explicitly extracted as fine-grained guidance, so that the model is guided to generate abstract texts with smoother semantics and more self-consistent logic.

Description

technical field [0001] The present invention relates to the field of artificial intelligence algorithms, and more specifically, to a method for generating summaries based on planning mechanisms and knowledge map guidance. Background technique [0002] Information on the Internet is growing exponentially, providing various content and information to hundreds of millions of Internet users. Users expect to be able to quickly and conveniently obtain the main information and read the abstract. However, at present, the abstract text generation and refinement of various long articles on the Internet are mainly completed by professional editors, which is not only time-consuming and labor-intensive, but also unsatisfactory. market demand. [0003] In recent years, with the development of artificial intelligence and big data, machine writing and text information summarization technology has made remarkable progress. Abstract automatic generation technology is gradually commercialize...

AI Technical Summary

Problems solved by technology

The application scenarios of generative summarization are more flexible, and the difficulties and problems are more challenging

[0004] Generative summarization mainly has two major limitations and challenges: first, computer programs are often unable to capture key information and understand complex semantic logic when inputting and processing source text, further, in the present invention; secondly, existing The automatic writing system is still unable to make good use of human knowledge and experience that is highly generalized and summarized to assist in the generation of texts, resulting in most of the generative summaries having logical contradictions, word order barriers, repetitions and other defects

Images