Automatic learning and extending evolution handling method for Chinese basic block descriptive rule

Abstract

The invention relates to a method for automatically learning and extended evolution about the description rules of Chinese basic blocks, and its characteristics are as follow: it rapidly excludes the unreliable description rules of the different stages to greatly increase the processing efficiency for automatically accessing rules through introducing a confidence evaluation mechanism. It opens a learning environment and breaks the constraint of automatically enhance the learning capacity for lack of training corpus through the introduction of external knowledge of the rules of evolutionary learning process for different languages. It continually introduces additional internal and external linkages vocabulary context restrictions knowledge from the original series described marker rules to dynamic-devise the state space of positive and negative cases, so that it gradually evolves the structure rules to form a hierarchical, multi-block sized of basic rules description system.

Description

technical field [0001] The invention belongs to the technical field of natural language processing Background technique [0002] In recent years, statistical-based processing methods have become the mainstream technology in the field of natural language processing research. The basic processing process is: for a certain processing problem, first construct a tagged corpus, then use machine learning methods to train a suitable language model from it, and form a complete information description of the problem through the combination of different parameters, and finally, for similar For new problems, this automatically learned language model can be used to give more reliable automatic analysis results. The processing advantage of this method is that it can easily integrate various language resources, and quickly train a more suitable language knowledge calculation model. It has been widely used and achieved good processing effect. However, the readability of knowledge acquisi...

AI Technical Summary

Problems solved by technology

These research works have proved the important role of vocabulary and contextual knowledge in improving the ability to describe rules from different aspects, but the vocabulary knowledge they use is still limited to the vocabulary information at a specific position in the training corpus, and does not involve different combinations of relationships between words , not to further introduce the external vocabulary knowledge base, which limits the improvement space of the description ability of the corresponding rules to a certain extent

Images