Multi-document auto-abstracting method facing to inquiry

Abstract

The invention relates to a multi-document auto-abstracting method facing to inquiry, which comprises the following steps: performing preprocessing on the inquiry and documents; performing topic segmentation and semantic paragraph clustering on the preprocessed documents to obtain subtopics; expressing the inquiry and the sentences in each of the subtopics in the form of a word frequency vector, and calculating the correlation measurement of the inquiry and the subtopics; screening the subtopics according to the correlation measurement of the inquiry and the subtopics, sequencing the subtopics according to the importance of the subtopics, and selecting the front T important subtopics to obtain an ordered sequence of the subtopics correlative with the inquiry; and circularly obtaining representative sentences from the subtopic sequence in turn, and connecting the representative sentences together to generate an abstract. The method uses the topic segmentation technique so that the abstract is in a limited length range and comprises the important information in a document set as much as possible, provides more targeted services, can adjust the content of the abstract according to a user inquiry topic, and can achieve the interactions with users.

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