Graph model-based automatic abstracting method

Abstract

The invention relates to the field of automatic abstracting, and discloses a graph model-based automatic abstracting method. According to the technical scheme, an LDA probability topic model is applied to measurement of semantic correlation between sentences and improvement of the measurement effect of sentence correlation; and an idea of topic correlation and position sensitivity of the sentences is provided, so that abstract generation is relatively reasonable and effective. The method comprises the following steps: firstly, obtaining topic probability distribution of a document and word probability distribution of the topic through training the LDA topic model, determining the topic probability distribution of the sentences and effectively converting a semantic similarity measurement between the sentences into a similarity measurement problem of the topic probability distribution of the sentences; with the sentences as nodes, building edges by referring tothe cosine similarity and according to the semantic similarity between the sentences and generating a text graph representing the document; calculating the topic correlation between the sentences according to the topic probability distribution of the sentences and the topic probability distribution of the document; and calculating the position sensitivity and the like of the sentences according to the positions of the sentences in the document.

Description

technical field [0001] The invention relates to the field of automatic summarization, in particular to an automatic summarization method based on a graph model. Background technique [0002] Automatic abstraction technology is to use computer to automatically process documents, generate a summary containing the core content of the original document, and realize the compression of documents, so that people can find and obtain the required information in less time, which can effectively solve information overload. question. [0003] Although automatic summarization has a long research history since 1960, the extraction-based summarization method, that is, directly extracting key sentences from the original text to generate summaries, is still the most mainstream method in this field. The core idea of ​​automatic summarization based on extraction is: first, statistically analyze the various features of sentences in one or more documents, calculate the importance of sentences, ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention will overcome the problem that it is difficult to accurately measure the semantic correlation between sentences and ignore some attributes of the text unit itself in the prior art, and provide an improved automatic summarization method based on the graph model

Images