Unlock instant, AI-driven research and patent intelligence for your innovation.

Large sentence library based translation method

A sentence library and sentence technology, applied in the field of language translation using machines, can solve problems such as grammatical errors and reduce translation accuracy, and achieve the effect of improving accuracy

Inactive Publication Date: 2017-06-13
SHENZHEN UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In different languages, there are many differences in the research and development of the gender, case, and number of nouns, the tense and conjugation of verbs, and the gender of adjectives. Therefore, grammatical errors will inevitably occur in the process of constructing sentences in the target language. Reduced translation accuracy

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
  • Large sentence library based translation method
  • Large sentence library based translation method
  • Large sentence library based translation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Example 1: Translate the Chinese "they are talking" into Uyghur, and select the source language as Chinese and the target language as Uyghur. The text input "they are talking", the search engine module finds the source sentence sentence "they are talking" from the source language large sentence library module, and the sentence call module finds the polysemous sentence library module and the synonymous sentence library module according to the source sentence. Multiple sentences of "they are eating", "they are talking about work", "they" and "they are eating" corresponding to the source sentence, and the source displayed by the user from the interface driven by the display module Among the sentences, polysemy sentences and synonymous sentences, select the sentence "they are talking" that is closest to the semantics you want to express, and the user selection module converts the sentence selected by the user into the corresponding sentence in the target language sentence li...

Embodiment 2

[0046] Example 2: Translate the Chinese sentence "I went to school" into English, select the source language as Chinese and the target language as English. The text input "I went to school", the search engine module finds the source sentence sentence from the source language sentence library module, and the sentence call module finds out the source sentence in the polysemous sentence library module and the synonymous sentence library module according to the source sentence. Corresponding polysemy sentences, "I went to school" is a polysemy sentence, which can be translated into English in different ways. If the question is "Where did you go yesterday?", the answer can be "I went to school." In this case, the translation should be "I went to school". If a student tells someone that he or she is going to school soon, and says "I am going to school", the translation should be "I am going to school". In order to avoid translation errors, two expressions are displayed on the ladde...

Embodiment 3

[0048] Example 3: Translate the Chinese sentence "This is my husband" into English, select the source language as Chinese and the target language as English. Text input "This is my husband", the search engine module does not find the source sentence sentence from the source language sentence library module, the search engine module sends the information that the source sentence sentence is not found to the sentence call-out module, and the sentence call-out module is in In the synonym library module, the synonyms that are synonymous with the input sentence "This is my husband", "This is my husband" and "This is my man" are found. According to the corresponding relationship between the synonym and the source sentence, Find the source sentence sentence "This is my husband", the user selects the sentence "This is my husband" that is closest to the semantics he wants to express from the source sentences and synonymous sentences displayed on the interface driven by the display modul...

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 large sentence library based translation method. The technical problem to be solved is to improve the accuracy of machine-based language translation. The method of the invention comprises the steps of setting a source language large-sentence-library module, a target language large-sentence-library module, a polysemous sentence library module, and a synonymous sentence library module; inputting a sentence to be translated; finding from the source language large-sentence-library module, source statement sentences the same as the input sentence; finding from the polysemous sentence library module and the synonymous sentence library module, polysemous sentences and synonymous sentences; selecting the sentences having the closest meaning; finding from the target language large-sentence-library module, corresponding sentences in target language. Compared with the prior art, the method replaces a word bank with a sentence library; the translation means of complete sentences corresponding to complete sentences is adopted, so that various grammar mistakes due to the process where a source language sentence is divided into single words that are translated to compose a sentence are avoided; handling by the polysemous sentences and synonymous sentences is adopted, so that translation accuracy is improved significantly.

Description

technical field [0001] The present invention relates to a method for language translation, in particular to a method for language translation using a machine. Background technique [0002] Machine translation of languages ​​first appeared in the 1940s and has been continuously improved with the advancement of computer technology. In the past ten years, the traditional machine translation systems and methods developed along the way have continued to improve. The mainstream state-of-the-art machine translation is to first establish a thesaurus or word library of the source language and the target language. When translating a sentence, the machine splits the input source language sentence into subject, predicate, object, adverbial and other components, and then according to the correspondence between the words in the two thesaurus, finds the corresponding words in the target language. The words in the target language are then formed into sentences to obtain the translated sen...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/28G06F17/27G06F17/30
CPCG06F16/243G06F40/211G06F40/42G06F40/58
Inventor 黄中伟
Owner SHENZHEN UNIV