Method for automatically correcting Mongolian
An automatic correction, Mongolian language technology, applied in natural language data processing, special data processing applications, instruments, etc., can solve problems such as error-prone
Active Publication Date: 2017-01-18
INNER MONGOLIA UNIVERSITY
View PDF3 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] In order to achieve the above object, the present invention provides a Mongolian automatic correction method, which uses intermediate codes to uniformly represent all Mongolian words in the text with the same appearance but different codes, and corrects the words in the set using a method based on dictionaries and rules , which solves the problem that the artificial statistical error input method in the prior art is easy to make mistakes and has great limitations
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0033] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0034] Mongolian automatic correction method of the present invention, as figure 1 As shown, firstly, the input Mongolian text is preprocessed, intermediate code conversion, and stem and affix segmentation are performed, and then the words in the set are corrected based on the dictionary and the rule-based method, and the unregistered words are not processed and output as they are; The converted polysyllabic homographs are output using the language model to select the optimal conversion result, and the converted monosyllabic homographs are output directly; finally, the correction results of the words in the set and the unregistered words are combined to obtain the corrected text.
[0035] Pre-processing: pre-processing includes two contents of Mongolian text clause and symbol processing; Mongolian text clause adopts rule-based sentence clause...
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
Login to View More Abstract
The invention discloses a method for automatically correcting Mongolian and belongs to the technical field of language correction. The method comprises the following steps: performing preprocessing and intermediate code conversion on the input Mongolian text, and performing stem and affix segmentation on the intermediate code to judge whether the words are the words in a set; correcting the words in the set by a method based on a dictionary and a rule, and not processing the unlisted words and outputting the original unlisted words; selecting an optimal conversion result from the converted homographic polyphonic words by a language model and outputting the optimal conversion result, and directly outputting homographic monosyllabic words; combining the correction results of the words in the set and the unlisted words to obtain a text which corrected. All the Mongolian words with the same display mode and different codes in the text are uniformly expressed by the intermediate codes, and the words in the set are corrected by the method based on the dictionary and the rule, so that the problems that the manual statistic error input method is error-prone and has high boundedness in the prior art are solved.
Description
technical field [0001] The invention belongs to the technical field of language correction and relates to an automatic Mongolian correction method. Background technique [0002] Mongolian is the main language of the Mongolian people and the main language of the Inner Mongolia Autonomous Region of my country. Since the Mongolian script is written very differently from Chinese and Western scripts, it is considered to be one of the most difficult scripts to informatize. It contains 35 letters. The different upper, middle, and lower positions of the letters in the word will lead to different writing styles, and some letters have the same appearance in the word. Since a considerable number of users only care about the correctness of the presentation form when entering Mongolian, they do not care about the correct spelling of Mongolian words, and randomly use the same presentation form to replace the correct letter. There are a large number of presentations in the existing Mongol...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27
CPCG06F40/232G06F40/289
Inventor 飞龙路敏高光来
Owner INNER MONGOLIA UNIVERSITY