Chinese text abstract generate method, computer-readable storage medium and computer device

Abstract

The invention relates to a method for generating text abstracts, a computer-readable storage medium and a computer device, comprising the steps of obtaining a word set of text and a word set of abstracts respectively; calculating the word frequency of each word in the word set of the text and the word set of the abstract Inverse document frequency, obtaining a text thesaurus and an abstract thesaurus, obtaining a fusion vector of each word in the text thesaurus and a fusion vector of each word in the abstract thesaurus; obtaining a word set of the text to be processed; obtaining a fusion vector of each word in a word set of the text to be processed; generating a summary word vector; according to the mapping relationship between each word in the abstract thesaurus and the fusion vector of each word in the abstract thesaurus, the word corresponding to the abstract thesaurus vector is obtained, and the word is outputted as the abstract. Using word frequency-reverse document frequency to obtain the vocabulary, so that some low-frequency vocabulary which can reflect the subject of the text can be retained, reducing the problem beyond the vocabulary, so that the generated abstract can more accurately express the meaning of the text vocabulary.

Description

technical field [0001] The invention relates to the field of text data processing, in particular to a method for generating text summaries, a computer-readable storage medium and computer equipment. Background technique [0002] With the explosive development of data, especially the rapid increase of text data, people have been unable to browse and understand all the texts of interest in time, but the omission of some important text data will cause a lot of organizational and application losses. Therefore, text summarization As the information that summarizes the important data of the text, it has become the focus of people's attention, and how to automatically generate summaries based on the text data has also become a hot research topic. [0003] At present, the existing methods for automatically generating text summaries mainly use the encoding-decoding model in machine learning. Specifically, the model first uses Recurrent Neural Networks (RNN) as an encoder to encode in...

AI Technical Summary

Problems solved by technology

When the new text contains some important words beyond the vocabulary, since the encoding-decoding model only uses the parameters learned in the training set, when generating, predict which word in the vocabulary should be selected for a certain position one by one , therefore, when generating a summary, only "UNK" can be used to replace these important words beyond the vocabulary, which makes the extracted summary inaccurate

Images