GENERATIVE AUTOMATIC abstracting METHOD BASED ON BERT AND EXTERNAL KNOWLES

Abstract

The invention belongs to the field of natural language processing, and particularly relates to a BERT and external knowledge-based generative automatic abstracting method, which comprises the following steps of: acquiring document data, and acquiring keywords corresponding to the document data through a TextRank module; inputting the document data into the BERT model for encoding to obtain encoded document information; external knowledge is retrieved from an external knowledge module through keywords, and the external knowledge and document information are fused through a gating mechanism; the fused information is input into a Transform model to be decoded, and an abstract is generated; according to the method, the BERT model is used for encoding the document data to capture more context information and internal information, the encoding quality is improved, the keyword is used for obtaining external knowledge to be fused with the document information, the Transform model is used for enriching the semantics of the generated abstract, the smoothness and integrity of the generated abstract are improved, and the high-quality abstract is generated.

Description

technical field [0001] The invention belongs to the field of natural language processing, and in particular relates to a generative automatic summarization method based on BERT and external knowledge. Background technique [0002] With the advancement of technology and the vigorous development of the mobile Internet industry, every netizen and even every terminal has become a producer of Internet information. In the face of massive amounts of information, the phenomenon of information overload is becoming more and more serious. How to enable people to efficiently obtain the information they need has become a great challenge in today's era. In order to obtain the required information more efficiently, automatic text summarization has gradually become an indispensable technology. [0003] Automatic text summarization can be divided into extractive automatic text summarization and generative automatic text summarization. Extractive summarization generates summaries by selecti...

AI Technical Summary

Problems solved by technology

[0004] The above technologies are based on the original document to directly generate abstracts. Compared with manually writing abstracts, external prior knowledge is not considered, resulting in the generated abstracts being unable to accurately express the purpose of the document, and it is difficult to ensure the coherence and consistency of the generated abstracts.

Images