Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Internet information natural language translation general method and system

A technology of natural language and semantics, which is applied in the field of Internet information semantics unified coding and human-assisted general translation methods and systems, which can solve problems such as limited market demand, unguaranteed translation quality, and difficulty in accurately solving the semantics of original symbols

Inactive Publication Date: 2008-06-11
刘莎
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the machine translation technology produced in the non-network era has never been able to occupy this obvious huge market: 1) Fully automatic translation - the fundamental problem that is difficult to solve is that the translation quality cannot be guaranteed
2) Human-assisted translation - users must understand the original text and the translation, and the market demand is very limited
Therefore, it is not only difficult to accurately solve the source symbol semantics by computational techniques alone (whether rule-based or statistical)
Moreover, even if the semantics of the original text is accurately solved, the automatically generated translation will have new understanding ambiguities in contexts other than sentences

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
  • Internet information natural language translation general method and system
  • Internet information natural language translation general method and system
  • Internet information natural language translation general method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Embodiment 1: The main flow of the application of the present invention, see Figures 1, 2, 3, 4, 5, and 6

[0054] Execute Figure 2 step 201: according to the user operation instruction, the user terminal (101-1 to 101-N) sends a terminal application program download request to the system business processing host (103) through the application server (102), receives and installs the slave database (106 ) downloaded terminal application

[0055] Execute step 202: According to the user operation instruction in 101-1, 101-1 invokes the human-computer interaction template of the original semantic unified coding, and the user inputs the original text to be translated as shown in Figure 3-1 or 3-3

[0056] Execute step 203: whether to automatically retrieve the original text with uniform encoding?

[0057] Execution step 204: yes, then 101-1 sends original text to 103, and 103 built-in search engine retrieves original text with received original text (comprising original text...

Embodiment 2

[0067] Example 2: The basic process of automatic semantic annotation of the original text, see Figure 7

[0068] Execute step 701, the original text semantic automatic encoding program automatically segments the words and phrases in the original sentence

[0069] Execute step 702, call all semantic items of the original text sentence vocabulary and phrase from the original text unified coded thesaurus and the syntax library according to the segmentation result,

[0070]Execute step 703, judge the syntactic component information item of original sentence, the missing syntactic component information item (such as sentence core component, core verb...), original text sentence vocabulary and the preferred semantic item of phrase according to effective sentence pattern collocation rule, will The discrimination results are displayed in the original semantic unified coding human-computer interaction template;

[0071] Execute step 704, adjust or confirm automatic preferred Unicode? ...

Embodiment 3

[0077] Example 3: The basic process of automatically generating translations and calling the translation browsing page, see Figure 8 and Figure 6

[0078] Execute step 801, the translation automatic conversion program transfers the unified coding object in the translation unified coding lexicon and syntax library with the semantic unified coding result of the original sentence;

[0079] Step 802 is executed, and the calling result is multiple coded objects? Yes, go to 803; No, go to 804

[0080] Execute step 803, optimize multiple objects of the same semantic code according to conditions such as the frequency of use of the coded object;

[0081] Execute step 804, according to the translation automatic conversion rules, use the translation vocabulary surface symbols in the translation coding object to automatically generate the translation, and use the semantic items in the translation coding object to automatically generate the translation semantic annotation results and call...

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 relates to an Internet information semantic unified coding artificial supplementary general translation method with sentence as unit and system, which has the advantages that: other random languages can be automatically translated as long as user adopts mother tongue to carry out a human-computer interaction to the original text; the translation semantic information transmission quality can be ensured; a plurality of languages translation results with reliable semantic information transmission quality can be realized even if user creates new words, new abbreviation and new fixed phrases and idiomatic expressions by himself; more users, the higher automation level of translation through the support of translation service center of the system. The invention is especially suitable for translation of natural languages of Internet communication information such as instant communication, e-mail, web page information, etc.

Description

technical field [0001] The present invention relates to a general method and system for Internet information natural language translation, more precisely, relates to a human-aided general translation method and system for Internet information semantics unified coding with sentences as units. technical background [0002] Since Internet communication has become popular all over the world, multilingual translation services for network information have become the common and common needs of hundreds of millions of users. However, the machine translation technology produced in the non-network era has never been able to occupy this obvious huge market: 1) Fully automatic translation - the fundamental problem that is difficult to solve is that the translation quality cannot be guaranteed. 2) Human-assisted translation - users must understand the original text and the translation, and the market demand is very limited. [0003] The root cause of the above pr...

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): G06F17/28G06F17/30
Inventor 刘莎
Owner 刘莎
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products