A Sentence Segmentation Method for Medical Ancient Chinese Based on Bayesian Statistical Learning

Abstract

The invention belongs to the field of language processing, and discloses a method for segmenting medical ancient Chinese sentences based on Bayesian statistical learning. On the basis of the Yeesian method, adding two-tuples and three-tuples to the feature attributes or combining various feature attributes of one-tuples, two-tuples, and three-tuples to obtain multiple sets of experimental data results, and finally get the best model; Then realize the medical ancient Chinese sentence segmentation task. The present invention is combined with the actual processing text content, and the F value of each feature of the prior art can be increased by at least 25 percentage points through this experimental method. In the present invention, the medical ancient Chinese text sentence recognition rules are systematically analyzed and summarized, and the realization of A processing method that can be applied to the actual field of traditional Chinese medicine and establishes a sentence recognition corpus of medical ancient Chinese texts, further allowing scientific research results to play a greater role.

Description

technical field [0001] The invention belongs to the field of language processing, in particular to a method for segmenting medical ancient Chinese sentences based on Bayesian statistical learning. Background technique [0002] Natural language processing technology has a strong language correlation. In foreign countries, relatively mature language processing technology has been applied to the text processing of medical information and patient case history, so as to help doctors extract key information from huge medical-related information data. , and transform it into an effective knowledge system, and then further apply it to related work. In China, major medical institutions in various provinces and cities across the country are also intensively working on the modern intelligent processing of big data in the medical field. in progress. [0003] A large number of medical Chinese ancient books are collected in libraries all over the country and major scientific research ins...

AI Technical Summary

Problems solved by technology

But nowadays, applying the more mature modern Chinese processing technology to the immature Chinese medical text processing technology in China, whether these methods are as good as in the modern text when facing the processing performance of the medical ancient Chinese text, does not matter. To be further verified

However, due to the inconsistency of the processing regulations and the lack of corpus for the required processing tasks, the technology that has been applied has resulted in low efficiency in the processing of classics. to violate

[0005] To sum up, the problem existing in the prior art is that the existing relatively mature modern Chinese processing technology is applied to the immature Chinese medical text processing technology in China. When these methods face the processing performance of medical ancient Chinese text, Whether it is as good as it is in modern texts remains to be further verified

Currently applied technology, due to the inconsistency of the regulations in the processing method and the lack of a large amount of corpus required for the processing task, the processing cost is high and the processing effect is low.

Images