A Query-Oriented Multi-Document Automatic Summarization Method

Abstract

The invention relates to a query-oriented multi-document automatic summarization method, comprising the following steps: preprocessing the query and the document; subjecting the preprocessed document to subject segmentation and semantic paragraph clustering to obtain subtopics; The sentences in each subtopic are expressed in the form of word frequency vectors, and the correlation between the query and the subtopic is calculated; according to the correlation between the query and the subtopic, the subtopics are screened, and the subtopics are sorted according to the importance of the subtopics, and the top T is selected. An important subtopic is obtained to obtain an ordered sequence of subtopics related to the query; representative sentences are cyclically extracted from the sequence of subtopics, and the representative sentences are connected to generate a summary. The method of the present invention uses the topic segmentation technology to make the abstract within a limited length range, including the more important information in the document set as much as possible, providing more targeted services, and adjusting the content of the abstract according to the user's query topic to realize the interaction with the user .

Description

technical field [0001] The invention relates to a natural language automatic summarization processing technology, in particular to a query-oriented multi-document automatic summarization method. Background technique [0002] With the rapid change and development of human society, a large amount of new information is produced every day, and the popularity of Internet technology makes the degree of information sharing higher and higher. People can easily publish information on the Internet, resulting in excessive information sources on the Internet. Many, a lot of information is repeated. For example, for the same news event, different news organizations may publish different reports, but the main content of the reports is similar or even completely repeated, and the only difference lies in the way of expression. This repetitive information wastes readers' reading time. On the other hand, different articles under the same topic will also cover some different information. Fo...

AI Technical Summary

Problems solved by technology

However, the existing methods mainly generate summaries based on the similarity between sentences and queries, without considering the distribution of subtopics in the summaries, often resulting in a large number of summary sentences from the same subtopic, although by calculating the text repetition, try to prevent duplication of content The summary sentence can alleviate this problem to a certain extent, but it still cannot guarantee the comprehensiveness of the information in the summary.

Images