Automatic special subject generating method based on book catalogue

Abstract

The invention discloses an automatic special subject generating method based on a book catalogue. For each book, each chapter in the catalogue is regarded as a word, features of the words are extracted, a classifier is trained out to recognize entities in the book catalogue, and a chapter pair meeting the hyponymy is extracted out for each pair of superior and subordinate chapter words belonging to the entities in the book catalogue. The concept hierarchical structure of each word is constructed according to the hyponymy, and the same or similar concept hierarchies in all the books are fused; for each concept word in the concept hierarchies, the content of the concept word in a webpage and a book is searched to serve as the description content of the word; finally, the concept hierarchies and the concept word contents are organized into the form of a special subject. By means of the automatic special subject generating method, the structured information of the book catalogue and a machine learning related algorithm are utilized, extraction and reorganization of knowledge are achieved, reference can be provided for compiling the special subject, the manpower cost of related work can be greatly reduced, and high practicability is achieved.

Description

technical field [0001] The invention relates to the fields of natural language processing and machine learning, in particular to a method for automatically generating topics based on book catalogs. Background technique [0002] With the rapid development of computer science and technology, network data is also growing explosively. These network data have the characteristics of wide sources, no structure, no hierarchy, complex components, and much noise. How to extract knowledge from it and organize and apply it in a certain way has become a hot topic in the fields of natural language processing, machine learning and information retrieval. Knowledge bases provide a feasible solution to this problem, however, the construction of large-scale knowledge bases is still a challenging task. WordNet, EurowordNet, and Cyc are all knowledge bases manually compiled by domain experts. Although they are of high quality, they are obviously insufficient in terms of scale, knowledge covera...

AI Technical Summary

Problems solved by technology

Although they are of high quality, they are obviously insufficient in terms of scale, knowledge coverage, update cycle, etc. In addition, manual writing requires a lot of manpower and material resources

In the context of big data, manual database construction is even more powerless

Images