Text core word recognition method and device

Abstract

The present application discloses a text core word recognition method and device, wherein the method includes: according to the first-level sample text, the first-level preferred core words of the first-level sample text, and the entity characteristics of the first-level preferred core words , training to obtain a conditional random field CRF model; from the keywords extracted for the secondary sample text by using the CRF model and at least one keyword extraction algorithm, select the secondary preferred core of the secondary sample text words; according to the secondary sample text and the secondary preferred core words, the deep neural network model is trained to obtain a text core word recognition model; and using the text core word recognition model to identify the core words of the target text. By applying this application, the recognition accuracy of the text core word recognition model can be improved through multi-level optimization of training samples, thereby improving the accuracy of the extracted core words.

Description

technical field [0001] The present disclosure generally relates to the field of Internet technology, and specifically relates to a text core word recognition method and device. Background technique [0002] With the development of computer and network technology, the number of digitized files is increasing at an alarming rate. People spend a lot of time and energy reading and searching for documents every day. In order to save time and improve people's work efficiency, various concise representations of original documents (such as abstracts, keywords, core words, etc.) have emerged as the times require. Core words are defined as words that compress important information and core content of the original text. People can use it to quickly understand the general content of the text without reading the full text. In information retrieval, core words are often used by us to find content-related text or pictures and videos carrying text. [0003] For example, through keyword-b...

AI Technical Summary

Problems solved by technology

[0006] Although there are existing solutions for automatically extracting core words in texts, the accuracy of the identified core words needs to be further improved

Images