Document Boltzmann machine construction optimization method and device for document query
The invention provides a document Boltzmann machine construction and optimization method for document query, which comprises the following steps of: sampling a selected document to obtain a pluralityof groups of text fragments, and gathering the obtained plurality of groups of text fragments to obta...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
19.05.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention provides a document Boltzmann machine construction and optimization method for document query, which comprises the following steps of: sampling a selected document to obtain a pluralityof groups of text fragments, and gathering the obtained plurality of groups of text fragments to obtain a sample set; performing model learning processing according to the sample set to obtain a document Boltzmann machine model corresponding to the selected document; and performing optimization processing on the generated document Boltzmann machine model through a Bayesian information criterion toobtain an optimized document Boltzmann machine model. According to the document Boltzmann machine construction and optimization method for document query provided by the invention, the Boltzmann machine is applied to the field of document query, the dependency relationship between lexical items can be naturally captured, and the distribution hypothesis used by a traditional language model is generalized. More effective qu |
---|---|
Bibliography: | Application Number: CN201811339382 |