Method for calculating language structure, executing participle, machine translation and speech recognition using HMM

A language structure and grammatical structure technology, applied in speech recognition, computing, speech analysis, etc., can solve problems such as improvement tends to limit, grammatical structure is incomplete, etc., to achieve reasonable data sparse problem, reduced style dependence, good expansion sexual effect

Inactive Publication Date: 2008-06-18
李萍
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the principle of the current related methods is usually to introduce the probability mechanism into the rule-based grammar such as context-free grammar or tree bank grammar. Although some improvements have been obtained, it can rely on probability means to choose when there are multiple syntactic analysis results. However, ...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for calculating language structure, executing participle, machine translation and speech recognition using HMM
  • Method for calculating language structure, executing participle, machine translation and speech recognition using HMM
  • Method for calculating language structure, executing participle, machine translation and speech recognition using HMM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] figure 1 shows the method of the present invention for computing language structure using a hidden Markov model, please refer to figure 1 , the following is a detailed description of each step in the process flow of the method.

[0044] Step S1: Establish a Hierarchical Building Block Grammar (GBBG) of the natural language.

[0045] The feature of GBBG grammar is that it provides the organic arrangement and interconnection of related language units on the plane or straight line to express the language structure, especially the way of language recursion and parallelism, that is, the grammatical structure of natural language is expressed by the directed graph data structure, especially is an arbitrary level of recursive pattern. More specifically, the relevant simple phrases and simple clauses are regarded as basic language building blocks, and ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method of modeling and calculating language structure by adopting hidden Markov models (HMM); the method can express and calculate the grammar structure of natural language effectively and completely, which more particularly expresses and calculates recursion and juxtaposition. The technical proposal is that: the GBBG grammar of the language is established; the HMM grammar of the language is established and the topological structure of LHMM is designed; the topological structure and parameters of the LHMM are trained and tested according to the HMM grammar; the grammar structure of sentences required to be analyzed is calculated by adopting the HMM theory and the topological structure of the LHMM and the parameters are regulated continuously according to the need. The invention is applied to the processing field of natural language.

Description

technical field [0001] The invention relates to a natural language processing method, in particular to a method for modeling and calculating natural language structure by using a hidden Markov model, and a method for performing natural language word segmentation, machine translation and speech recognition using the method. Background technique [0002] The language model (LM) used for speech recognition is usually a statistical N-gram model, while the one used for syntactic analysis is usually a context-free grammar (CFG) based on production rules. Although the N-gram model has achieved some success in speech recognition, it still has considerable limitations. Some of these limitations are: it cannot express the grammatical dependencies between long-distance linguistic units in a language, nor can it give the syntactic structure in a sentence. [0003] Context-free grammars, already used in some language technology products, often use thousands of hand-coded rules to descri...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/27G10L15/14G10L15/18
Inventor 李萍
Owner 李萍
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap