Multilingual automatic abstract method

Abstract

The invention relates to the technical field of text generation in natural language processing. The invention relates to a method, in particular to a multilingual automatic abstract method. INCLUDINGA Whole AUTOMATIC ABNORMATION SYSTEM, the automatic abstract system is divided into a model training module; a single-document abstract module and a multi-document abstract module, the model trainingmodule is divided into a text preprocessing module and a training module; wherein the single-document summary module is divided into a text preprocessing module and a summary generation module, the multi-document summary module is divided into a text preprocessing module, a multi-language sentence clustering module and a summary generation module, a model in the model training module is a seq2seqneural network model, and a training text is obtained through summary-summary generation. According to the invention, a multilingual generative automatic abstract system is designed and realized, a bilingual word embedding technology and a deep learning method are adopted, and a brief abstract is generated for a text or a text set specified by a user, so that the user is helped to browse intentions of an original text and quickly find out the most required information.

Description

technical field [0001] The invention relates to the technical field of text generation in natural language processing, in particular to a multilingual automatic summarization method. Background technique [0002] Text summarization usually refers to generating a piece of text from a single or multiple documents, which conveys the main information in the original text, but only has less than half or even less space than the original text. For example, summarizing a 1500-word text into a 150-word abstract can save readers a lot of reading time and also play a role in information compression. [0003] According to the generation method of the abstract, we can divide automatic summarization into extractive summarization (Extractive Summarization) and generative summarization (Abstractive Summarization). Among them, the feature of the extractive summary is that the sentences in the summary are sentences in the original text, also called "sentence excerpts", while the feature of ...

AI Technical Summary

Problems solved by technology

[0010] (1) The sentences extracted by the traditional extractive summary contain a lot of redundant information, and the coherence between the sentences is not strong, and the readability is poor, while the length of the generative summary is short, the redundancy is low, and the generalization of the sentence is strong ;

[0011] (2) Multilingual automatic summarization based on machine translation is relatively simple. Translate texts in different languages ​​into one language and then perform automatic summarization. This method is heavily dependent on the quality of machine translation results and has low execution efficiency.

Images