Method utilizing Chinese online resources for supervising extraction of character relations remotely

Abstract

The invention discloses a method utilizing Chinese online resources for supervising extraction of character relations remotely. According to the method, at first, an online encyclopedia website, formed through a semi-manual mode, on a web is utilized for automatically constructing a knowledge base so as to obtain accurate relation types comprehensive as much as possible, and examples of the character relations; then co-occurring names and context features are extracted from a text corpus, and the names and the relation examples in the knowledge base are matched to obtain name pair sets of the marked relations and name pair sets of unmarked relations; finally, a label propagation algorithm is introduced to achieve relation match of unmarked name pairs, so that extraction of the character relations is achieved. According to the method, the knowledge base of the character relations can be automatically constructed, and the richer and more accurate relation types are included; based on the knowledge base, the label propagation algorithm is introduced to supervise extraction of the character relations remotely, and therefore accuracy of results of the extracted relations can be ensured.

Description

technical field [0001] The technical fields involved in the present invention include webpage information crawling, text preprocessing, feature extraction, character pair similarity calculation, label propagation algorithm, etc., wherein text preprocessing includes technologies such as sentence segmentation, word segmentation, part-of-speech tagging, and name recognition. In general, the present invention is an effective extraction method for Chinese character relationships in the field of relationship extraction, which utilizes a large number of online resources and adopts a remote supervised learning method to extract character relationships. Background technique [0002] In natural language processing (NLP), information extraction is an important research field and has been widely used in practice. Information extraction refers to the extraction of structured information from natural texts to help people quickly find useful information from massive amounts of information....

AI Technical Summary

Problems solved by technology

However, the semi-supervised learning method has the following shortcomings: 1) Continuous iteration is prone to semantic drift, thereby reducing the accuracy rate; 2) It is necessary to define the relationship types of characters in advance, which may lead to the definition of relationship types is not comprehensive enough, such as defined in previous methods None of the relationship types covers the infrequent relationships such as "hostile" and "neighborhood"

However, in the extraction of Chinese character relationships, the remote supervision method has not been applied for a long time, which is necessarily related to the lack of a large-scale available Chinese relationship knowledge base.

Images