Automatic writing method based on extraction type multi-document abstract method

Abstract

The invention relates to an automatic writing method based on an extraction type multi-document abstract method, which comprises the following steps of A1, user input and data preprocessing of receiving a keyword inputted by a user, retrieving the related data on a data retrieval platform, and performing the preliminary processing on the retrieved related data; A2, graph sorting of inputting a plurality of documents, firstly identifying all sentences by the system, and scoring the importance of all the sentences; A3, redundancy removal of if two or more sentences with the similarity exceedinga preset threshold exist in the sentences, only reserving one sentence, and outputting an ordered sentence list with redundant sentences removed; and A4, constructing and outputting, selecting the most important sentences from the ordered sentence list provided in the previous stage according to the limitation of the text from front to back, reordering the sentences, and outputting a manuscript formed by the ordered sentences.

Description

Technical field [0001] The invention belongs to computer applications, computer systems, the Internet, information processing and its technical products. Background technique [0002] Automated writing for news refers to the application of intelligent algorithms that cooperate with computer software systems and big data resources. The writing system completes the writing of a news article through data collection, sorting, analysis and integration. Since 2010, foreign media such as the Associated Press, domestic media such as Xinhua News Agency and Tencent News have launched their own writing robots. The current writing is mainly for writing in the fields of finance, sports, and emergencies such as extreme weather and earthquakes. At present, the characteristics of these automatic writing systems are that the format of the information source is fixed and highly refined, and the output manuscripts are generally short in length. The realization method is mostly by using a template m...

AI Technical Summary

Problems solved by technology

However, at present, generative summarization based on deep learning is still far from the actual deployment and application. First, it cannot handle long texts, especially for multiple documents. Second, the generalization ability is very poor. The effect of training and testing on the set is often very poor on other data sets. Finally, the generated language itself often has language problems, partial repetitions, etc.

Images