Automatic quotation extraction method and device with semantic integrity kept

Abstract

The invention provides an automatic quotation extraction method and device. Characters or character strings, serving as reading focuses, in a text can be used in the method and device to serve as centers to automatically extract contexts, the length of an extracted quotation is within the preserved length scope, it is kept that the extracted quotation has the semantic integrity, a section of semantic scene which is appropriate in length and integral in meaning and enables the selected characters or the selected character strings to serve as the reading focuses can be extracted from the text and formed, and a user can conveniently restore the correct meaning of the reading focuses in the contexts.

Description

technical field [0001] The present application relates to text analysis and extraction technology, and more specifically, to a method and device for automatic citation extraction while maintaining semantic integrity. Background technique [0002] In electronic structured documents, it is very necessary in many application scenarios to extract citation text centered on some keywords, phrases, sentences, etc. that are manually selected by the user or automatically selected based on predetermined rules (such as matching rules, etc.). function. For example, in the process of reading documents such as web pages, users can use marking tools to select the reading focus that they are interested in for reference in other reading; when users want to share these reading focuses through social networks such as Weibo, Only relying on the marked keywords, phrases and sentences is not enough for readers to restore the context of the reading focus, and cannot understand the meaning of the ...

AI Technical Summary

Problems solved by technology

The obvious defect of this method is that the generated citations often do not have semantic integrity. It often happens that half of a sentence is included in the citation and the other half is not included in the citation, or even a word is truncated, which makes readers read. I don't know why

Moreover, in some cases, such integrity-breaking and truncated citations will affect users' ability to use them. For example, if the text contains information such as e-mail addresses, URL web page addresses, phone numbers, etc., and the citations truncate these information, then all Citations provided will not be of any real value

[0007] It can be seen that none of the existing citation extraction technologies can keep the semantic integrity of the citation under the premise of keeping the length of the citation within the threshold value, and avoid cutting off integral strings such as complete sentences, vocabulary, and email addresses. meet people's needs

Images