Method for automatically recognizing semanteme of natural language sentences understood by computer

Abstract

The invention relates to a method for automatically recognizing the semanteme of natural language sentences understood by a computer, in particular to a method for accurately recognizing the Chinese language, which comprises the following specific steps: a, establishing a body base in a certain filed; b, establishing a semantic framework knowledge base on the basis of a field body; and c, directly matching the natural language sentences with semantic structures on the basis of the body mapping of semantic frameworks, and recognizing the matching according to the modes of the semantic frameworks. The method is very different from the mainstream method of segmenting words in the second-generation search engine technology. The segmented words have concept annotations of the field body, the accurate semantic matching of the natural language sentences can be obtained hereby, and the computer system can carry out calculation and inference on the body knowledge, therefore, the deep artificial intelligent question and answer has a wide prospect of application.

Description

Technical field [0001] The present invention involves a method of computer identification of human language, and specially involves a method that can accurately identify Chinese language. Background technique [0002] The working principle of the search engine is based on keyword matching, cutting the user's input, turning a sentence into a short word, and then entering the background database to match the keywords of the web content.In the result of the search return, as long as these keywords are with these keywords, they will return, including a large amount of irrelevant information, the check rate is low, and the real intention of the user cannot be cut. [0003] Obviously, the sync and search technology based on keyword matching limits the automatic analysis capabilities of the computer in retrieval.For a sentence to match and cut the keywords, although it is easy to handle a sentence made of keywords, it is difficult to understand a sentence in the form of natural language...

AI Technical Summary

Problems solved by technology

[0007]1. Syntax analysis is based on thesaurus, which needs to accumulate a large-scale corpus to achieve preliminary semantic annotation, and the construction cost is huge;

[0008]2. The thesaurus does not distinguish between domains, and each word only has grammatical meaning, such as noun, verb, adverbial, subject, object, etc., but lacks clear semantic meaning

[0009]3. Since the corpus is a large collection of words, in order to adapt to different domain characteristics, cumbersome learning algorithms are required when using them, and the reuse is low , the system performance is difficult to meet the practical requirements of the commercial production environment, so it cannot go out of the laboratory;

[0010]In short, this semantic role-based annotation is too coarse-grained, and the understanding of sentence meaning cannot meet the requirements of deep artificial intelligence question answering